ref.bib

@article{wu2020comprehensive,
  title={A comprehensive survey on graph neural networks},
  author={Wu, Zonghan and Pan, Shirui and Chen, Fengwen and Long, Guodong and Zhang, Chengqi and Philip, S Yu},
  journal={IEEE transactions on neural networks and learning systems},
  year={2020},
  publisher={IEEE}
}

@article{defferrard2016convolutional,
  title={Convolutional neural networks on graphs with fast localized spectral filtering},
  author={Defferrard, Micha{\"e}l and Bresson, Xavier and Vandergheynst, Pierre},
  journal={arXiv preprint arXiv:1606.09375},
  year={2016}
}

@article{liao2019lanczosnet,
  title={Lanczosnet: Multi-scale deep graph convolutional networks},
  author={Liao, Renjie and Zhao, Zhizhen and Urtasun, Raquel and Zemel, Richard S},
  journal={arXiv preprint arXiv:1901.01484},
  year={2019}
}

@article{yun2019graph,
  title={Graph transformer networks},
  author={Yun, Seongjun and Jeong, Minbyul and Kim, Raehyun and Kang, Jaewoo and Kim, Hyunwoo J},
  journal={arXiv preprint arXiv:1911.06455},
  year={2019}
}

@article{bianchi2021graph,
  title={Graph neural networks with convolutional arma filters},
  author={Bianchi, Filippo Maria and Grattarola, Daniele and Livi, Lorenzo and Alippi, Cesare},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2021},
  publisher={IEEE}
}

@article{choromanski2020rethinking,
  title={Rethinking attention with performers},
  author={Choromanski, Krzysztof and Likhosherstov, Valerii and Dohan, David and Song, Xingyou and Gane, Andreea and Sarlos, Tamas and Hawkins, Peter and Davis, Jared and Mohiuddin, Afroz and Kaiser, Lukasz and others},
  journal={arXiv preprint arXiv:2009.14794},
  year={2020}
}

@misc{balcilar2020bridging,
    title={Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks},
    author={Muhammet Balcilar and Guillaume Renton and Pierre Heroux and Benoit Gauzere and Sebastien Adam and Paul Honeine},
    year={2020},
    eprint={2003.11702},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

@article{nilsson2020experimental,
  title={An Experimental Study of the Transferability of Spectral Graph Networks},
  author={Nilsson, Axel and Bresson, Xavier},
  journal={arXiv preprint arXiv:2012.10258},
  year={2020}
}

@inproceedings{trivedi2019dyrep,
  title={Dyrep: Learning representations over dynamic graphs},
  author={Trivedi, Rakshit and Farajtabar, Mehrdad and Biswal, Prasenjeet and Zha, Hongyuan},
  booktitle={International Conference on Learning Representations},
  year={2019}
}

@article{kazemi2019relational,
  title={Relational representation learning for dynamic (knowledge) graphs: A survey},
  author={Kazemi, Seyed Mehran and Goel, Rishab and Jain, Kshitij and Kobyzev, Ivan and Sethi, Akshay and Forsyth, Peter and Poupart, Pascal},
  journal={arXiv preprint arXiv:1905.11485},
  year={2019}
}

@article{poli2019graph,
  title={Graph neural ordinary differential equations},
  author={Poli, Michael and Massaroli, Stefano and Park, Junyoung and Yamashita, Atsushi and Asama, Hajime and Park, Jinkyoo},
  journal={arXiv preprint arXiv:1911.07532},
  year={2019}
}

@inproceedings{zang2020neural,
  title={Neural dynamics on complex networks},
  author={Zang, Chengxi and Wang, Fei},
  booktitle={Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining},
  pages={892--902},
  year={2020}
}

@inproceedings{han2020graph,
  title={Graph Hawkes Neural Network for Forecasting on Temporal Knowledge Graphs},
  author={Han, Zhen and Ma, Yunpu and Wang, Yuyi and Gunnemann, Stephan and Tresp, Volker},
  booktitle={Automated Knowledge Base Construction},
  year={2020}
}

@article{liu2021learning,
  title={Learning Representation over Dynamic Graph using Aggregation-Diffusion Mechanism},
  author={Liu, Mingyi and Tu, Zhiying and Xu, Xiaofei and Wang, Zhongjie},
  journal={arXiv preprint arXiv:2106.01678},
  year={2021}
}

@inproceedings{taheri2019learning,
  title={Learning to represent the evolution of dynamic graphs with recurrent models},
  author={Taheri, Aynaz and Gimpel, Kevin and Berger-Wolf, Tanya},
  booktitle={Companion Proceedings of The 2019 World Wide Web Conference},
  pages={301--307},
  year={2019}
}

@article{liu2018darts,
  title={Darts: Differentiable architecture search},
  author={Liu, Hanxiao and Simonyan, Karen and Yang, Yiming},
  journal={arXiv preprint arXiv:1806.09055},
  year={2018}
}

@article{denil2013predicting,
  title={Predicting parameters in deep learning},
  author={Denil, Misha and Shakibi, Babak and Dinh, Laurent and Ranzato, Marc'Aurelio and De Freitas, Nando},
  journal={arXiv preprint arXiv:1306.0543},
  year={2013}
}

@article{ha2016hypernetworks,
  title={Hypernetworks},
  author={Ha, David and Dai, Andrew and Le, Quoc V},
  journal={arXiv preprint arXiv:1609.09106},
  year={2016}
}

@article{zhang2018graph,
  title={Graph hypernetworks for neural architecture search},
  author={Zhang, Chris and Ren, Mengye and Urtasun, Raquel},
  journal={arXiv preprint arXiv:1810.05749},
  year={2018}
}

@article{cai2019once,
  title={Once-for-all: Train one network and specialize it for efficient deployment},
  author={Cai, Han and Gan, Chuang and Wang, Tianzhe and Zhang, Zhekai and Han, Song},
  journal={arXiv preprint arXiv:1908.09791},
  year={2019}
}

@article{bertinetto2016learning,
  title={Learning feed-forward one-shot learners},
  author={Bertinetto, Luca and Henriques, Jo{\~a}o F and Valmadre, Jack and Torr, Philip HS and Vedaldi, Andrea},
  journal={arXiv preprint arXiv:1606.05233},
  year={2016}
}


@incollection{Bengio+chapter2007,
author = {Bengio, Yoshua and LeCun, Yann},
booktitle = {Large Scale Kernel Machines},
publisher = {MIT Press},
title = {Scaling Learning Algorithms Towards {AI}},
year = {2007}
}

@article{Hinton06,
author = {Hinton, Geoffrey E. and Osindero, Simon and Teh, Yee Whye},
journal = {Neural Computation},
pages = {1527--1554},
title = {A Fast Learning Algorithm for Deep Belief Nets},
volume = {18},
year = {2006}
}

@book{goodfellow2016deep,
title={Deep learning},
author={Goodfellow, Ian and Bengio, Yoshua and Courville, Aaron and Bengio, Yoshua},
volume={1},
year={2016},
publisher={MIT Press}
}

@article{bronstein2017geometric,
  title={Geometric deep learning: going beyond euclidean data},
  author={Bronstein, Michael M and Bruna, Joan and LeCun, Yann and Szlam, Arthur and Vandergheynst, Pierre},
  journal={IEEE Signal Processing Magazine},
  volume={34},
  number={4},
  pages={18--42},
  year={2017},
  publisher={IEEE}
}

@inproceedings{monti2017geometric,
  title={Geometric deep learning on graphs and manifolds using mixture model CNNs},
  author={Monti, Federico and Boscaini, Davide and Masci, Jonathan and Rodola, Emanuele and Svoboda, Jan and Bronstein, Michael M},
  booktitle={Proc. CVPR},
  volume={1},
  number={2},
  pages={3},
  year={2017}
}


@techreport{krizhevsky2009learning,
  title={Learning multiple layers of features from tiny images},
  author={Krizhevsky, Alex},
  year={2009},
  institution={Citeseer}
}

@inproceedings{kipf2016semi,
  title={Semi-supervised classification with graph convolutional networks},
  author={Kipf, Thomas N and Welling, Max},
  booktitle={International Conference on Learning Representations (ICLR)},
  journal={arXiv preprint arXiv:1609.02907},
  year={2017}
}

@article{henaff2015deep,
  title={Deep convolutional networks on graph-structured data},
  author={Henaff, Mikael and Bruna, Joan and LeCun, Yann},
  journal={arXiv preprint arXiv:1506.05163},
  year={2015}
}

@inproceedings{bruna2013spectral,
  title={Spectral networks and locally connected networks on graphs},
  author={Bruna, Joan and Zaremba, Wojciech and Szlam, Arthur and LeCun, Yann},
  booktitle={International Conference on Learning Representations (ICLR)},
  journal={arXiv preprint arXiv:1312.6203},
  year={2014}
}

@inproceedings{fey2018splinecnn,
  title={SplineCNN: Fast geometric deep learning with continuous B-spline kernels},
  author={Fey, Matthias and Lenssen, Jan Eric and Weichert, Frank and M{\"u}ller, Heinrich},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={869--877},
  year={2018}
}

@article{lecun1998gradient,
  title={Gradient-based learning applied to document recognition},
  author={LeCun, Yann and Bottou, L{\'e}on and Bengio, Yoshua and Haffner, Patrick},
  journal={Proceedings of the IEEE},
  volume={86},
  number={11},
  pages={2278--2324},
  year={1998},
  publisher={IEEE}
}

@inproceedings{simonovsky2017dynamic,
  title={Dynamic edgeconditioned filters in convolutional neural networks on graphs},
  author={Simonovsky, Martin and Komodakis, Nikos},
  booktitle={Proc. CVPR},
  year={2017}
}

@inproceedings{niepert2016learning,
  title={Learning convolutional neural networks for graphs},
  author={Niepert, Mathias and Ahmed, Mohamed and Kutzkov, Konstantin},
  booktitle={Proceedings of the 33rd International Conference on Machine Learning (ICML)},
  pages={2014--2023},
  year={2016}
}

@article{shervashidze2011weisfeiler,
  title={Weisfeiler-lehman graph kernels},
  author={Shervashidze, Nino and Schweitzer, Pascal and Leeuwen, Erik Jan van and Mehlhorn, Kurt and Borgwardt, Karsten M},
  journal={Journal of Machine Learning Research},
  volume={12},
  number={Sep},
  pages={2539--2561},
  year={2011}
}

@inproceedings{dai2016discriminative,
  title={Discriminative embeddings of latent variable models for structured data},
  author={Dai, Hanjun and Dai, Bo and Song, Le},
  booktitle={Proceedings of the 33rd International Conference on Machine Learning (ICML)},
  pages={2702--2711},
  year={2016}
}

@inproceedings{zhang2018end,
  title={An end-to-end deep learning architecture for graph classification},
  author={Zhang, Muhan and Cui, Zhicheng and Neumann, Marion and Chen, Yixin},
  booktitle={Proceedings of AAAI Conference on Artificial Inteligence},
  year={2018}
}

@article{boldi2014axioms,
  title={Axioms for centrality},
  author={Boldi, Paolo and Vigna, Sebastiano},
  journal={Internet Mathematics},
  volume={10},
  number={3-4},
  pages={222--262},
  year={2014},
  publisher={Taylor \& Francis}
}

@article{zhou2016semantic,
  title={Semantic understanding of scenes through the ADE20K dataset},
  author={Zhou, Bolei and Zhao, Hang and Puig, Xavier and Fidler, Sanja and Barriuso, Adela and Torralba, Antonio},
  journal={arXiv preprint arXiv:1608.05442},
  year={2016}
}

@inproceedings{zhao2017pyramid,
  title={Pyramid scene parsing network},
  author={Zhao, Hengshuang and Shi, Jianping and Qi, Xiaojuan and Wang, Xiaogang and Jia, Jiaya},
  booktitle={IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  pages={2881--2890},
  year={2017}
}

@inproceedings{lin2017refinenet,
  title={RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation.},
  author={Lin, Guosheng and Milan, Anton and Shen, Chunhua and Reid, Ian D},
  booktitle={Cvpr},
  volume={1},
  number={2},
  pages={5},
  year={2017}
}

@article{xie2017relating,
  title={Relating Input Concepts to Convolutional Neural Network Decisions},
  author={Xie, Ning and Sarker, Md Kamruzzaman and Doran, Derek and Hitzler, Pascal and Raymer, Michael},
  journal={arXiv preprint arXiv:1711.08006},
  year={2017}
}

@inproceedings{liang2016semantic,
  title={Semantic object parsing with graph lstm},
  author={Liang, Xiaodan and Shen, Xiaohui and Feng, Jiashi and Lin, Liang and Yan, Shuicheng},
  booktitle={European Conference on Computer Vision},
  pages={125--143},
  year={2016},
  organization={Springer}
}

@article{chen2018deeplab,
  title={Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs},
  author={Chen, Liang-Chieh and Papandreou, George and Kokkinos, Iasonas and Murphy, Kevin and Yuille, Alan L},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  volume={40},
  number={4},
  pages={834--848},
  year={2018},
  publisher={IEEE}
}

@inproceedings{jin2017multi,
  title={Multi-Path Feedback Recurrent Neural Networks for Scene Parsing.},
  author={Jin, Xiaojie and Chen, Yunpeng and Jie, Zequn and Feng, Jiashi and Yan, Shuicheng},
  booktitle={AAAI},
  volume={3},
  pages={8},
  year={2017}
}

@inproceedings{liang2018dynamic,
  title={Dynamic-structured Semantic Propagation Network},
  author={Liang, Xiaodan and Zhou, Hongfei and Xing, Eric},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={752--761},
  year={2018}
}

@inproceedings{xia2016zoom,
  title={Zoom better to see clearer: Human and object parsing with hierarchical auto-zoom net},
  author={Xia, Fangting and Wang, Peng and Chen, Liang-Chieh and Yuille, Alan L},
  booktitle={European Conference on Computer Vision},
  pages={648--663},
  year={2016},
  organization={Springer}
}

@inproceedings{shrivastava2014new,
  title={A new space for comparing graphs},
  author={Shrivastava, Anshumali and Li, Ping},
  booktitle={Proceedings of the 2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining},
  pages={62--71},
  year={2014},
  organization={IEEE Press}
}

@article{leskovec2007graph,
  title={Graph evolution: Densification and shrinking diameters},
  author={Leskovec, Jure and Kleinberg, Jon and Faloutsos, Christos},
  journal={ACM Transactions on Knowledge Discovery from Data (TKDD)},
  volume={1},
  number={1},
  pages={2},
  year={2007},
  publisher={ACM}
}


@article{hamilton2017representation,
  title={Representation learning on graphs: Methods and applications},
  author={Hamilton, William L and Ying, Rex and Leskovec, Jure},
  journal={arXiv preprint arXiv:1709.05584},
  year={2017}
}

@inproceedings{schlichtkrull2018modeling,
  title={Modeling relational data with graph convolutional networks},
  author={Schlichtkrull, Michael and Kipf, Thomas N and Bloem, Peter and van den Berg, Rianne and Titov, Ivan and Welling, Max},
  booktitle={European Semantic Web Conference},
  pages={593--607},
  year={2018},
  organization={Springer}
}

@article{levie2017cayleynets,
  title={Cayleynets: Graph convolutional neural networks with complex rational spectral filters},
  author={Levie, Ron and Monti, Federico and Bresson, Xavier and Bronstein, Michael M},
  journal={arXiv preprint arXiv:1705.07664},
  year={2017}
}

@inproceedings{bordes2013translating,
  title={Translating embeddings for modeling multi-relational data},
  author={Bordes, Antoine and Usunier, Nicolas and Garcia-Duran, Alberto and Weston, Jason and Yakhnenko, Oksana},
  booktitle={Advances in neural information processing systems},
  pages={2787--2795},
  year={2013}
}

@article{battaglia2018relational,
  title={Relational inductive biases, deep learning, and graph networks},
  author={Battaglia, Peter W and Hamrick, Jessica B and Bapst, Victor and Sanchez-Gonzalez, Alvaro and Zambaldi, Vinicius and Malinowski, Mateusz and Tacchetti, Andrea and Raposo, David and Santoro, Adam and Faulkner, Ryan and others},
  journal={arXiv preprint arXiv:1806.01261},
  year={2018}
}

@inproceedings{gilmer2017neural,
  title={Neural Message Passing for Quantum Chemistry},
  author={Gilmer, Justin and Schoenholz, Samuel S and Riley, Patrick F and Vinyals, Oriol and Dahl, George E},
  booktitle={Proceedings of the 34th International Conference on Machine Learning (ICML)},
  pages={1263--1272},
  year={2017}
}

@article{hammond2011wavelets,
  title={Wavelets on graphs via spectral graph theory},
  author={Hammond, David K and Vandergheynst, Pierre and Gribonval, R{\'e}mi},
  journal={Applied and Computational Harmonic Analysis},
  volume={30},
  number={2},
  pages={129--150},
  year={2011},
  publisher={Elsevier}
}

@inproceedings{duvenaud2015convolutional,
  title={Convolutional networks on graphs for learning molecular fingerprints},
  author={Duvenaud, David K and Maclaurin, Dougal and Iparraguirre, Jorge and Bombarell, Rafael and Hirzel, Timothy and Aspuru-Guzik, Al{\'a}n and Adams, Ryan P},
  booktitle={Advances in neural information processing systems},
  pages={2224--2232},
  year={2015}
}

@inproceedings{omar2010two,
  title={Two-dimensional Chebyshev polynomials for image fusion.},
  author={Omar, Zaid and Mitianoudis, Nikolaos and Stathaki, Tania},
  year={2010},
}

@article{kim2016hadamard,
  title={Hadamard product for low-rank bilinear pooling},
  author={Kim, Jin-Hwa and On, Kyoung-Woon and Lim, Woosang and Kim, Jeonghee and Ha, Jung-Woo and Zhang, Byoung-Tak},
  journal={arXiv preprint arXiv:1610.04325},
  year={2016}
}

@inproceedings{hamilton2017inductive,
  title={Inductive representation learning on large graphs},
  author={Hamilton, Will and Ying, Zhitao and Leskovec, Jure},
  booktitle={Advances in Neural Information Processing Systems},
  pages={1024--1034},
  year={2017}
}

@article{dhillon2007weighted,
  title={Weighted graph cuts without eigenvectors a multilevel approach},
  author={Dhillon, Inderjit S and Guan, Yuqiang and Kulis, Brian},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  volume={29},
  number={11},
  year={2007},
  publisher={IEEE}
}

@article{springenberg2014striving,
  title={Striving for simplicity: The all convolutional net},
  author={Springenberg, Jost Tobias and Dosovitskiy, Alexey and Brox, Thomas and Riedmiller, Martin},
  journal={arXiv preprint arXiv:1412.6806},
  year={2014}
}

@inproceedings{kingma2014adam,
  title={Adam: A method for stochastic optimization},
  author={Kingma, Diederik P and Ba, Jimmy},
  booktitle={International Conference on Learning Representations (ICLR)},
  journal={arXiv preprint arXiv:1412.6980},
  year={2015}
}

@article{wale2008comparison,
  title={Comparison of descriptor spaces for chemical compound retrieval and classification},
  author={Wale, Nikil and Watson, Ian A and Karypis, George},
  journal={Knowledge and Information Systems},
  volume={14},
  number={3},
  pages={347--375},
  year={2008},
  publisher={Springer}
}

@article{schomburg2004brenda,
  title={BRENDA, the enzyme database: updates and major new developments},
  author={Schomburg, Ida and Chang, Antje and Ebeling, Christian and Gremse, Marion and Heldt, Christian and Huhn, Gregor and Schomburg, Dietmar},
  journal={Nucleic acids research},
  volume={32},
  number={suppl\_1},
  pages={D431--D433},
  year={2004},
  publisher={Oxford University Press}
}

@article{debnath1991structure,
  title={Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. correlation with molecular orbital energies and hydrophobicity},
  author={Debnath, Asim Kumar and Lopez de Compadre, Rosa L and Debnath, Gargi and Shusterman, Alan J and Hansch, Corwin},
  journal={Journal of medicinal chemistry},
  volume={34},
  number={2},
  pages={786--797},
  year={1991},
  publisher={ACS Publications}
}

@article{borgwardt2005protein,
  title={Protein function prediction via graph kernels},
  author={Borgwardt, Karsten M and Ong, Cheng Soon and Sch{\"o}nauer, Stefan and Vishwanathan, SVN and Smola, Alex J and Kriegel, Hans-Peter},
  journal={Bioinformatics},
  volume={21},
  number={suppl\_1},
  pages={i47--i56},
  year={2005},
  publisher={Oxford University Press}
}

@misc{KKMMN2016,
  title  = {Benchmark Data Sets for Graph Kernels},
  author = {Kristian Kersting and Nils M. Kriege and Christopher Morris and Petra Mutzel and Marion Neumann},
  year   = {2016},
  url    = {http://graphkernels.cs.tu-dortmund.de}
}

@article{hinton2012improving,
  title={Improving neural networks by preventing co-adaptation of feature detectors},
  author={Hinton, Geoffrey E and Srivastava, Nitish and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan R},
  journal={arXiv preprint arXiv:1207.0580},
  year={2012}
}

@article{achanta2012slic,
	title={SLIC superpixels compared to state-of-the-art superpixel methods},
	author={Achanta, Radhakrishna and Shaji, Appu and Smith, Kevin and Lucchi, Aurelien and Fua, Pascal and S{\"u}sstrunk, Sabine},
	journal={IEEE transactions on pattern analysis and machine intelligence},
	volume={34},
	number={11},
	pages={2274--2282},
	year={2012},
	publisher={IEEE}
}

@article{simonyan2014very,
  title={Very deep convolutional networks for large-scale image recognition},
  author={Simonyan, Karen and Zisserman, Andrew},
  journal={arXiv preprint arXiv:1409.1556},
  year={2014}
}

@article{russakovsky2015imagenet,
  title={Imagenet large scale visual recognition challenge},
  author={Russakovsky, Olga and Deng, Jia and Su, Hao and Krause, Jonathan and Satheesh, Sanjeev and Ma, Sean and Huang, Zhiheng and Karpathy, Andrej and Khosla, Aditya and Bernstein, Michael and others},
  journal={International Journal of Computer Vision},
  volume={115},
  number={3},
  pages={211--252},
  year={2015},
  publisher={Springer}
}

@article{everingham2010pascal,
  title={The pascal visual object classes (voc) challenge},
  author={Everingham, Mark and Van Gool, Luc and Williams, Christopher KI and Winn, John and Zisserman, Andrew},
  journal={International journal of computer vision},
  volume={88},
  number={2},
  pages={303--338},
  year={2010},
  publisher={Springer}
}

@inproceedings{kriege2016valid,
	title={On valid optimal assignment kernels and applications to graph classification},
	author={Kriege, Nils M and Giscard, Pierre-Louis and Wilson, Richard},
	booktitle={Advances in Neural Information Processing Systems},
	pages={1623--1631},
	year={2016}
}

@inproceedings{de2013unsupervised,
	title={Unsupervised feature learning for classification of outdoor 3d scans},
	author={De Deuge, Mark}
}

@inproceedings{chen2018iterative,
	author = {Xinlei Chen and Li-Jia Li and Li Fei-Fei and Abhinav Gupta},
	title = {Iterative Visual Reasoning Beyond Convolutions},
	booktitle = {Proc. CVPR},
	Year = {2018}
}

@inproceedings{knyazev2018spectral,
	title={Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules},
	author={Knyazev, Boris and Lin, Xiao and Amer, Mohamed R and Taylor, Graham W},
	booktitle={NeurIPS Workshop on Machine Learning for Molecules and Materials},
	journal={arXiv preprint arXiv:1811.09595},
	year={2018}
}

@inproceedings{xu2018how,
	title={How Powerful are Graph Neural Networks?},
	author={Keyulu Xu and Weihua Hu and Jure Leskovec and Stefanie Jegelka},
	booktitle={International Conference on Learning Representations (ICLR)},
	year={2019}
}

@inproceedings{velivckovic2018deep,
	title={Deep graph infomax},
	author={Veli{\v{c}}kovi{\'c}, Petar and Fedus, William and Hamilton, William L and Li{\`o}, Pietro and Bengio, Yoshua and Hjelm, R Devon},
	booktitle={International Conference on Learning Representations (ICLR)},
	journal={arXiv preprint arXiv:1809.10341},
	year={2019}
}

@inproceedings{ying2018hierarchical,
	title={Hierarchical graph representation learning with differentiable pooling},
	author={Ying, Zhitao and You, Jiaxuan and Morris, Christopher and Ren, Xiang and Hamilton, Will and Leskovec, Jure},
	booktitle={Advances in Neural Information Processing Systems},
	pages={4805--4815},
	year={2018}
}

@inproceedings{ioffe2015batch,
	author = {Ioffe, Sergey and Szegedy, Christian},
	title = {Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift},
	booktitle={Proceedings of the 32nd International Conference on Machine Learning (ICML)},
	year = {2015}
} 


@article{srivastava2014dropout,
	title={Dropout: a simple way to prevent neural networks from overfitting},
	author={Srivastava, Nitish and Hinton, Geoffrey and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan},
	journal={The Journal of Machine Learning Research},
	volume={15},
	number={1},
	pages={1929--1958},
	year={2014},
	publisher={JMLR. org}
}

@inproceedings{simonovsky2018graphvae,
	title={Graphvae: Towards generation of small graphs using variational autoencoders},
	author={Simonovsky, Martin and Komodakis, Nikos},
	booktitle={International Conference on Artificial Neural Networks},
	pages={412--422},
	year={2018},
	organization={Springer}
}

@article{arbelaez2010contour,
	title={Contour detection and hierarchical image segmentation},
	author={Arbelaez, Pablo and Maire, Michael and Fowlkes, Charless and Malik, Jitendra},
	journal={IEEE transactions on pattern analysis and machine intelligence},
	volume={33},
	number={5},
	pages={898--916},
	year={2010},
	publisher={IEEE}
}

@inproceedings{graphunet2018,
	title={Graph {U-Net}},
	author={Gao, Hongyang and Ji, Shuiwang},
	booktitle={Proceedings of the 36th International Conference on Machine Learning (ICML)},
	year={2019}
}

@inproceedings{khasanova2017graph,
	title={Graph-based isometry invariant representation learning},
	author={Khasanova, Renata and Frossard, Pascal},
	booktitle={Proceedings of the 34th International Conference on Machine Learning-Volume 70},
	pages={1847--1856},
	year={2017},
	organization={JMLR. org}
}

@inproceedings{prabhu2015attribute,
	title={Attribute-graph: A graph based approach to image ranking},
	author={Prabhu, Nikita and Venkatesh Babu, R},
	booktitle={Proceedings of the IEEE International Conference on Computer Vision},
	pages={1071--1079},
	year={2015}
}



@article{kiros2014unifying,
  title={Unifying visual-semantic embeddings with multimodal neural language models},
  author={Kiros, Ryan and Salakhutdinov, Ruslan and Zemel, Richard S},
  journal={arXiv preprint arXiv:1411.2539},
  year={2014}
}


@article{smith2017don,
  title={Don't decay the learning rate, increase the batch size},
  author={Smith, Samuel L and Kindermans, Pieter-Jan and Ying, Chris and Le, Quoc V},
  journal={arXiv preprint arXiv:1711.00489},
  year={2017}
}


@inproceedings{hu2019language,
  title={Language-conditioned graph networks for relational reasoning},
  author={Hu, Ronghang and Rohrbach, Anna and Darrell, Trevor and Saenko, Kate},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={10294--10303},
  year={2019}
}

@inproceedings{beckham2019adversarial,
  title={On Adversarial Mixup Resynthesis},
  author={Beckham, Christopher and Honari, Sina and Verma, Vikas and Lamb, Alex M and Ghadiri, Farnoosh and Hjelm, R Devon and Bengio, Yoshua and Pal, Chris},
  booktitle={Advances in Neural Information Processing Systems},
  pages={4348--4359},
  year={2019}
}


@article{rong2019truly,
  title={The truly deep graph convolutional networks for node classification},
  author={Rong, Yu and Huang, Wenbing and Xu, Tingyang and Huang, Junzhou},
  journal={arXiv preprint arXiv:1907.10903},
  year={2019}
}

@article{cogswell2015reducing,
  title={Reducing overfitting in deep networks by decorrelating representations},
  author={Cogswell, Michael and Ahmed, Faruk and Girshick, Ross and Zitnick, Larry and Batra, Dhruv},
  journal={arXiv preprint arXiv:1511.06068},
  year={2015}
}

@inproceedings{wang2020orthogonal,
  title={Orthogonal convolutional neural networks},
  author={Wang, Jiayun and Chen, Yubei and Chakraborty, Rudrasis and Yu, Stella X},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={11505--11515},
  year={2020}
}

@article{bansal2018can,
  title={Can we gain more from orthogonality regularizations in training deep cnns?},
  author={Bansal, Nitin and Chen, Xiaohan and Wang, Zhangyang},
  journal={arXiv preprint arXiv:1810.09102},
  year={2018}
}

@inproceedings{huang2018decorrelated,
  title={Decorrelated batch normalization},
  author={Huang, Lei and Yang, Dawei and Lang, Bo and Deng, Jia},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={791--800},
  year={2018}
}

@article{rodriguez2016regularizing,
  title={Regularizing cnns with locally constrained decorrelations},
  author={Rodr{\'\i}guez, Pau and Gonzalez, Jordi and Cucurull, Guillem and Gonfaus, Josep M and Roca, Xavier},
  journal={arXiv preprint arXiv:1611.01967},
  year={2016}
}

@article{ghiasi2018dropblock,
  title={Dropblock: A regularization method for convolutional networks},
  author={Ghiasi, Golnaz and Lin, Tsung-Yi and Le, Quoc V},
  journal={arXiv preprint arXiv:1810.12890},
  year={2018}
}

@article{locatello2020object,
  title={Object-centric learning with slot attention},
  author={Locatello, Francesco and Weissenborn, Dirk and Unterthiner, Thomas and Mahendran, Aravindh and Heigold, Georg and Uszkoreit, Jakob and Dosovitskiy, Alexey and Kipf, Thomas},
  journal={arXiv preprint arXiv:2006.15055},
  year={2020}
}

@article{burgess2019monet,
  title={Monet: Unsupervised scene decomposition and representation},
  author={Burgess, Christopher P and Matthey, Loic and Watters, Nicholas and Kabra, Rishabh and Higgins, Irina and Botvinick, Matt and Lerchner, Alexander},
  journal={arXiv preprint arXiv:1901.11390},
  year={2019}
}


@article{engelcke2019genesis,
  title={Genesis: Generative scene inference and sampling with object-centric latent representations},
  author={Engelcke, Martin and Kosiorek, Adam R and Jones, Oiwi Parker and Posner, Ingmar},
  journal={arXiv preprint arXiv:1907.13052},
  year={2019}
}


@inproceedings{andreas2016neural,
  title={Neural module networks},
  author={Andreas, Jacob and Rohrbach, Marcus and Darrell, Trevor and Klein, Dan},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={39--48},
  year={2016}
}

@inproceedings{hu2017learning,
  title={Learning to reason: End-to-end module networks for visual question answering},
  author={Hu, Ronghang and Andreas, Jacob and Rohrbach, Marcus and Darrell, Trevor and Saenko, Kate},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={804--813},
  year={2017}
}

@inproceedings{stone2017teaching,
  title={Teaching compositionality to cnns},
  author={Stone, Austin and Wang, Huayan and Stark, Michael and Liu, Yi and Scott Phoenix, D and George, Dileep},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5058--5067},
  year={2017}
}

@article{sylvain2019locality,
  title={Locality and compositionality in zero-shot learning},
  author={Sylvain, Tristan and Petrini, Linda and Hjelm, Devon},
  journal={arXiv preprint arXiv:1912.12179},
  year={2019}
}

@inproceedings{naeem2021learning,
  title={Learning graph embeddings for compositional zero-shot learning},
  author={Naeem, Muhammad Ferjad and Xian, Yongqin and Tombari, Federico and Akata, Zeynep},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={953--962},
  year={2021}
}

@article{ruis2021independent,
  title={Independent Prototype Propagation for Zero-Shot Compositionality},
  author={Ruis, Frank and Burghours, Gertjan and Bucur, Doina},
  journal={arXiv preprint arXiv:2106.00305},
  year={2021}
}

@inproceedings{tokmakov2019learning,
  title={Learning compositional representations for few-shot recognition},
  author={Tokmakov, Pavel and Wang, Yu-Xiong and Hebert, Martial},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={6372--6381},
  year={2019}
}

@article{baradad2021learning,
  title={Learning to See by Looking at Noise},
  author={Baradad, Manel and Wulff, Jonas and Wang, Tongzhou and Isola, Phillip and Torralba, Antonio},
  journal={arXiv preprint arXiv:2106.05963},
  year={2021}
}

@inproceedings{demirel2017attributes2classname,
  title={Attributes2classname: A discriminative model for attribute-based unsupervised zero-shot learning},
  author={Demirel, Berkan and Gokberk Cinbis, Ramazan and Ikizler-Cinbis, Nazli},
  booktitle={Proceedings of the IEEE international conference on computer vision},
  pages={1232--1241},
  year={2017}
}

@inproceedings{ul2019explaining,
  title={Explaining visual classification using attributes},
  author={ul Hassan, Muneeb and Mulhem, Philippe and Pellerin, Denis and Qu{\'e}not, Georges},
  booktitle={2019 International Conference on Content-Based Multimedia Indexing (CBMI)},
  pages={1--6},
  year={2019},
  organization={IEEE}
}

@inproceedings{zeiler2014visualizing,
  title={Visualizing and understanding convolutional networks},
  author={Zeiler, Matthew D and Fergus, Rob},
  booktitle={European conference on computer vision},
  pages={818--833},
  year={2014},
  organization={Springer}
}

@article{kaneko2021debiasing,
  title={Debiasing pre-trained contextualised embeddings},
  author={Kaneko, Masahiro and Bollegala, Danushka},
  journal={arXiv preprint arXiv:2101.09523},
  year={2021}
}

@article{lowe2004distinctive,
  title={Distinctive image features from scale-invariant keypoints},
  author={Lowe, David G},
  journal={International journal of computer vision},
  volume={60},
  number={2},
  pages={91--110},
  year={2004},
  publisher={Springer}
}

@inproceedings{long2015fully,
  title={Fully convolutional networks for semantic segmentation},
  author={Long, Jonathan and Shelhamer, Evan and Darrell, Trevor},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={3431--3440},
  year={2015}
}

@article{simonyan2014two,
  title={Two-stream convolutional networks for action recognition in videos},
  author={Simonyan, Karen and Zisserman, Andrew},
  journal={arXiv preprint arXiv:1406.2199},
  year={2014}
}

@article{vondrick2016generating,
  title={Generating videos with scene dynamics},
  author={Vondrick, Carl and Pirsiavash, Hamed and Torralba, Antonio},
  journal={Advances in neural information processing systems},
  volume={29},
  pages={613--621},
  year={2016}
}

@inproceedings{dosovitskiy2015flownet,
  title={Flownet: Learning optical flow with convolutional networks},
  author={Dosovitskiy, Alexey and Fischer, Philipp and Ilg, Eddy and Hausser, Philip and Hazirbas, Caner and Golkov, Vladimir and Van Der Smagt, Patrick and Cremers, Daniel and Brox, Thomas},
  booktitle={Proceedings of the IEEE international conference on computer vision},
  pages={2758--2766},
  year={2015}
}

@article{wang2017video,
  title={Video salient object detection via fully convolutional networks},
  author={Wang, Wenguan and Shen, Jianbing and Shao, Ling},
  journal={IEEE Transactions on Image Processing},
  volume={27},
  number={1},
  pages={38--49},
  year={2017},
  publisher={IEEE}
}

@inproceedings{shelhamer2016clockwork,
  title={Clockwork convnets for video semantic segmentation},
  author={Shelhamer, Evan and Rakelly, Kate and Hoffman, Judy and Darrell, Trevor},
  booktitle={European Conference on Computer Vision},
  pages={852--868},
  year={2016},
  organization={Springer}
}

@article{gu2018recent,
  title={Recent advances in convolutional neural networks},
  author={Gu, Jiuxiang and Wang, Zhenhua and Kuen, Jason and Ma, Lianyang and Shahroudy, Amir and Shuai, Bing and Liu, Ting and Wang, Xingxing and Wang, Gang and Cai, Jianfei and others},
  journal={Pattern Recognition},
  volume={77},
  pages={354--377},
  year={2018},
  publisher={Elsevier}
}

@article{levie2018cayleynets,
  title={Cayleynets: Graph convolutional neural networks with complex rational spectral filters},
  author={Levie, Ron and Monti, Federico and Bresson, Xavier and Bronstein, Michael M},
  journal={IEEE Transactions on Signal Processing},
  volume={67},
  number={1},
  pages={97--109},
  year={2018},
  publisher={IEEE}
}

@article{tong2020directed,
  title={Directed graph convolutional network},
  author={Tong, Zekun and Liang, Yuxuan and Sun, Changsheng and Rosenblum, David S and Lim, Andrew},
  journal={arXiv preprint arXiv:2004.13970},
  year={2020}
}

@inproceedings{zhu2020simple,
  title={Simple spectral graph convolution},
  author={Zhu, Hao and Koniusz, Piotr},
  booktitle={International Conference on Learning Representations},
  year={2020}
}

@article{hu2020open,
  title={Open graph benchmark: Datasets for machine learning on graphs},
  author={Hu, Weihua and Fey, Matthias and Zitnik, Marinka and Dong, Yuxiao and Ren, Hongyu and Liu, Bowen and Catasta, Michele and Leskovec, Jure},
  journal={arXiv preprint arXiv:2005.00687},
  year={2020}
}

@article{szegedy2013intriguing,
  title={Intriguing properties of neural networks},
  author={Szegedy, Christian and Zaremba, Wojciech and Sutskever, Ilya and Bruna, Joan and Erhan, Dumitru and Goodfellow, Ian and Fergus, Rob},
  journal={arXiv preprint arXiv:1312.6199},
  year={2013}
}

@article{schott2018towards,
  title={Towards the first adversarially robust neural network model on MNIST},
  author={Schott, Lukas and Rauber, Jonas and Bethge, Matthias and Brendel, Wieland},
  journal={arXiv preprint arXiv:1805.09190},
  year={2018}
}

@inproceedings{mascharka2018transparency,
  title={Transparency by design: Closing the gap between performance and interpretability in visual reasoning},
  author={Mascharka, David and Tran, Philip and Soklaski, Ryan and Majumdar, Arjun},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={4942--4950},
  year={2018}
}

@article{lust2020survey,
  title={A Survey on Assessing the Generalization Envelope of Deep Neural Networks at Inference Time for Image Classification},
  author={Lust, Julia and Condurache, Alexandru Paul},
  journal={arXiv preprint arXiv:2008.09381},
  year={2020}
}


@article{klinger2020study,
  title={A Study of Compositional Generalization in Neural Models},
  author={Klinger, Tim and Adjodah, Dhaval and Marois, Vincent and Joseph, Josh and Riemer, Matthew and Pentland, Alex'Sandy' and Campbell, Murray},
  journal={arXiv preprint arXiv:2006.09437},
  year={2020}
}

@article{hupkes2019compositionality,
  title={The compositionality of neural networks: integrating symbolism and connectionism},
  author={Hupkes, Dieuwke and Dankers, Verna and Mul, Mathijs and Bruni, Elia},
  journal={arXiv preprint arXiv:1908.08351},
  year={2019}
}

@article{clevert2015fast,
  title={Fast and accurate deep network learning by exponential linear units (elus)},
  author={Clevert, Djork-Arn{\'e} and Unterthiner, Thomas and Hochreiter, Sepp},
  journal={arXiv preprint arXiv:1511.07289},
  year={2015}
}

@inproceedings{maas2013rectifier,
  title={Rectifier nonlinearities improve neural network acoustic models},
  author={Maas, Andrew L and Hannun, Awni Y and Ng, Andrew Y and others},
  booktitle={Proc. icml},
  volume={30},
  number={1},
  pages={3},
  year={2013},
  organization={Citeseer}
}

@article{touvron2021resmlp,
  title={Resmlp: Feedforward networks for image classification with data-efficient training},
  author={Touvron, Hugo and Bojanowski, Piotr and Caron, Mathilde and Cord, Matthieu and El-Nouby, Alaaeldin and Grave, Edouard and Joulin, Armand and Synnaeve, Gabriel and Verbeek, Jakob and J{\'e}gou, Herv{\'e}},
  journal={arXiv preprint arXiv:2105.03404},
  year={2021}
}

@inproceedings{ciregan2012multi,
  title={Multi-column deep neural networks for image classification},
  author={Ciregan, Dan and Meier, Ueli and Schmidhuber, J{\"u}rgen},
  booktitle={2012 IEEE conference on computer vision and pattern recognition},
  pages={3642--3649},
  year={2012},
  organization={IEEE}
}

@incollection{fukushima1982neocognitron,
  title={Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition},
  author={Fukushima, Kunihiko and Miyake, Sei},
  booktitle={Competition and cooperation in neural nets},
  pages={267--285},
  year={1982},
  publisher={Springer}
}

@inproceedings{vedaldi2015matconvnet,
  title={Matconvnet: Convolutional neural networks for matlab},
  author={Vedaldi, Andrea and Lenc, Karel},
  booktitle={Proceedings of the 23rd ACM international conference on Multimedia},
  pages={689--692},
  year={2015}
}

@inproceedings{belkin2001laplacian,
  title={Laplacian eigenmaps and spectral techniques for embedding and clustering.},
  author={Belkin, Mikhail and Niyogi, Partha},
  booktitle={Nips},
  volume={14},
  number={14},
  pages={585--591},
  year={2001}
}

@book{chung1997spectral,
  title={Spectral graph theory},
  author={Chung, Fan RK and Graham, Fan Chung},
  number={92},
  year={1997},
  publisher={American Mathematical Soc.}
}

@inproceedings{wu2019simplifying,
  title={Simplifying graph convolutional networks},
  author={Wu, Felix and Souza, Amauri and Zhang, Tianyi and Fifty, Christopher and Yu, Tao and Weinberger, Kilian},
  booktitle={International conference on machine learning},
  pages={6861--6871},
  year={2019},
  organization={PMLR}
}

@article{sperduti1997supervised,
  title={Supervised neural networks for the classification of structures},
  author={Sperduti, Alessandro and Starita, Antonina},
  journal={IEEE Transactions on Neural Networks},
  volume={8},
  number={3},
  pages={714--735},
  year={1997},
  publisher={IEEE}
}

@article{dwivedi2020generalization,
  title={A generalization of transformer networks to graphs},
  author={Dwivedi, Vijay Prakash and Bresson, Xavier},
  journal={arXiv preprint arXiv:2012.09699},
  year={2020}
}

@inproceedings{you2018graphrnn,
  title={Graphrnn: Generating realistic graphs with deep auto-regressive models},
  author={You, Jiaxuan and Ying, Rex and Ren, Xiang and Hamilton, William and Leskovec, Jure},
  booktitle={International conference on machine learning},
  pages={5708--5717},
  year={2018},
  organization={PMLR}
}

@article{liao2019efficient,
  title={Efficient graph generation with graph recurrent attention networks},
  author={Liao, Renjie and Li, Yujia and Song, Yang and Wang, Shenlong and Nash, Charlie and Hamilton, William L and Duvenaud, David and Urtasun, Raquel and Zemel, Richard S},
  journal={arXiv preprint arXiv:1910.00760},
  year={2019}
}

@article{li2018beyond,
  title={Beyond grids: Learning graph representations for visual recognition},
  author={Li, Yin and Gupta, Abhinav},
  journal={Advances in Neural Information Processing Systems},
  volume={31},
  pages={9225--9235},
  year={2018}
}

@article{zhang2019dual,
  title={Dual graph convolutional network for semantic segmentation},
  author={Zhang, Li and Li, Xiangtai and Arnab, Anurag and Yang, Kuiyuan and Tong, Yunhai and Torr, Philip HS},
  journal={arXiv preprint arXiv:1909.06121},
  year={2019}
}

@inproceedings{meyer2020large,
  title={Large-scale graph networks and AI applied to medical image data processing},
  author={Meyer-B{\"a}se, Anke and Foo, Simon and Tahmassebi, Amirhessam and Meyer-B{\"a}se, Uwe and Amani, Ali Moradi and G{\"o}tz, Theresa and Leithner, Doris and Stadlbauer, Andreas and Pinker, Katja},
  booktitle={Computational Imaging V},
  volume={11396},
  pages={1139605},
  year={2020},
  organization={International Society for Optics and Photonics}
}

@article{zhang2018neural,
  title={Neural guided constraint logic programming for program synthesis},
  author={Zhang, Lisa and Rosenblatt, Gregory and Fetaya, Ethan and Liao, Renjie and Byrd, William E and Might, Matthew and Urtasun, Raquel and Zemel, Richard},
  journal={arXiv preprint arXiv:1809.02840},
  year={2018}
}

@inproceedings{kipf2018neural,
  title={Neural relational inference for interacting systems},
  author={Kipf, Thomas and Fetaya, Ethan and Wang, Kuan-Chieh and Welling, Max and Zemel, Richard},
  booktitle={International Conference on Machine Learning},
  pages={2688--2697},
  year={2018},
  organization={PMLR}
}

@article{gunning2019darpa,
  title={DARPA’s explainable artificial intelligence (XAI) program},
  author={Gunning, David and Aha, David},
  journal={AI Magazine},
  volume={40},
  number={2},
  pages={44--58},
  year={2019}
}

@article{jiang2019language,
  title={Language as an abstraction for hierarchical deep reinforcement learning},
  author={Jiang, Yiding and Gu, Shixiang and Murphy, Kevin and Finn, Chelsea},
  journal={arXiv preprint arXiv:1906.07343},
  year={2019}
}

@inproceedings{kipf2019compile,
  title={Compile: Compositional imitation learning and execution},
  author={Kipf, Thomas and Li, Yujia and Dai, Hanjun and Zambaldi, Vinicius and Sanchez-Gonzalez, Alvaro and Grefenstette, Edward and Kohli, Pushmeet and Battaglia, Peter},
  booktitle={International Conference on Machine Learning},
  pages={3418--3428},
  year={2019},
  organization={PMLR}
}

@article{cogswell2019emergence,
  title={Emergence of compositional language with deep generational transmission},
  author={Cogswell, Michael and Lu, Jiasen and Lee, Stefan and Parikh, Devi and Batra, Dhruv},
  journal={arXiv preprint arXiv:1904.09067},
  year={2019}
}


@article{agrawal2017c,
  title={C-vqa: A compositional split of the visual question answering (vqa) v1. 0 dataset},
  author={Agrawal, Aishwarya and Kembhavi, Aniruddha and Batra, Dhruv and Parikh, Devi},
  journal={arXiv preprint arXiv:1704.08243},
  year={2017}
}

@inproceedings{agrawal2018don,
  title={Don't just assume; look and answer: Overcoming priors for visual question answering},
  author={Agrawal, Aishwarya and Batra, Dhruv and Parikh, Devi and Kembhavi, Aniruddha},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={4971--4980},
  year={2018}
}

@inproceedings{hjelm2018learning,
 author = {R Devon Hjelm and Alex Fedorov and Samuel Lavoie-Marchildon and Karan Grewal and Phil Bachman and Adam Trischler and Yoshua Bengio},
 booktitle = {International Conference on Learning Representations},
 title = {Learning deep representations by mutual information estimation and maximization},
 url = {https://openreview.net/forum?id=Bklr3j0cKX},
 year = {2019}
}


@inproceedings{ganin2015unsupervised,
  title={Unsupervised domain adaptation by backpropagation},
  author={Ganin, Yaroslav and Lempitsky, Victor},
  booktitle={International conference on machine learning},
  pages={1180--1189},
  year={2015},
  organization={PMLR}
}

@inproceedings{lee2019self,
  title={Self-attention graph pooling},
  author={Lee, Junhyun and Lee, Inyeop and Kang, Jaewoo},
  booktitle={International Conference on Machine Learning},
  pages={3734--3743},
  year={2019},
  organization={PMLR}
}

@article{shaham2018spectralnet,
  title={Spectralnet: Spectral clustering using deep neural networks},
  author={Shaham, Uri and Stanton, Kelly and Li, Henry and Nadler, Boaz and Basri, Ronen and Kluger, Yuval},
  journal={arXiv preprint arXiv:1801.01587},
  year={2018}
}

@article{dittadi2021generalization,
  title={Generalization and Robustness Implications in Object-Centric Learning},
  author={Dittadi, Andrea and Papa, Samuele and De Vita, Michele and Sch{\"o}lkopf, Bernhard and Winther, Ole and Locatello, Francesco},
  journal={arXiv preprint arXiv:2107.00637},
  year={2021}
}

@article{russell2007object,
  title={Object recognition by scene alignment},
  author={Russell, Bryan and Torralba, Antonio and Liu, Ce and Fergus, Rob and Freeman, William},
  journal={Advances in Neural Information Processing Systems},
  volume={20},
  pages={1241--1248},
  year={2007}
}

@article{fodor1988connectionism,
  title={Connectionism and cognitive architecture: A critical analysis},
  author={Fodor, Jerry A and Pylyshyn, Zenon W},
  journal={Cognition},
  volume={28},
  number={1-2},
  pages={3--71},
  year={1988},
  publisher={Elsevier}
}

@inproceedings{lake2018generalization,
  title={Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks},
  author={Lake, Brenden and Baroni, Marco},
  booktitle={International conference on machine learning},
  pages={2873--2882},
  year={2018},
  organization={PMLR}
}

@article{yi2018neural,
  title={Neural-symbolic vqa: Disentangling reasoning from vision and language understanding},
  author={Yi, Kexin and Wu, Jiajun and Gan, Chuang and Torralba, Antonio and Kohli, Pushmeet and Tenenbaum, Joshua B},
  journal={arXiv preprint arXiv:1810.02338},
  year={2018}
}

@article{galloway2018adversarial,
  title={Adversarial training versus weight decay},
  author={Galloway, Angus and Tanay, Thomas and Taylor, Graham W},
  journal={arXiv preprint arXiv:1804.03308},
  year={2018}
}

@inproceedings{long2017deep,
  title={Deep transfer learning with joint adaptation networks},
  author={Long, Mingsheng and Zhu, Han and Wang, Jianmin and Jordan, Michael I},
  booktitle={International conference on machine learning},
  pages={2208--2217},
  year={2017},
  organization={PMLR}
}

@article{wang2018dataset,
  title={Dataset distillation},
  author={Wang, Tongzhou and Zhu, Jun-Yan and Torralba, Antonio and Efros, Alexei A},
  journal={arXiv preprint arXiv:1811.10959},
  year={2018}
}

@article{gadermayr2019cnn,
  title={CNN cascades for segmenting sparse objects in gigapixel whole slide images},
  author={Gadermayr, Michael and Dombrowski, Ann-Kathrin and Klinkhammer, Barbara Mara and Boor, Peter and Merhof, Dorit},
  journal={Computerized Medical Imaging and Graphics},
  volume={71},
  pages={40--48},
  year={2019},
  publisher={Elsevier}
}

@inproceedings{johnson2017inferring,
  title={Inferring and executing programs for visual reasoning},
  author={Johnson, Justin and Hariharan, Bharath and Van Der Maaten, Laurens and Hoffman, Judy and Fei-Fei, Li and Lawrence Zitnick, C and Girshick, Ross},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={2989--2998},
  year={2017}
}

@inproceedings{choromanska2015loss,
  title={The loss surfaces of multilayer networks},
  author={Choromanska, Anna and Henaff, Mikael and Mathieu, Michael and Arous, G{\'e}rard Ben and LeCun, Yann},
  booktitle={Artificial intelligence and statistics},
  pages={192--204},
  year={2015},
  organization={PMLR}
}

@article{chetlur2014cudnn,
  title={cudnn: Efficient primitives for deep learning},
  author={Chetlur, Sharan and Woolley, Cliff and Vandermersch, Philippe and Cohen, Jonathan and Tran, John and Catanzaro, Bryan and Shelhamer, Evan},
  journal={arXiv preprint arXiv:1410.0759},
  year={2014}
}

@article{corso2020principal,
  title={Principal neighbourhood aggregation for graph nets},
  author={Corso, Gabriele and Cavalleri, Luca and Beaini, Dominique and Li{\`o}, Pietro and Veli{\v{c}}kovi{\'c}, Petar},
  journal={arXiv preprint arXiv:2004.05718},
  year={2020}
}

@article{shaw2018self,
  title={Self-attention with relative position representations},
  author={Shaw, Peter and Uszkoreit, Jakob and Vaswani, Ashish},
  journal={arXiv preprint arXiv:1803.02155},
  year={2018}
}

@inproceedings{karras2020analyzing,
  title={Analyzing and improving the image quality of stylegan},
  author={Karras, Tero and Laine, Samuli and Aittala, Miika and Hellsten, Janne and Lehtinen, Jaakko and Aila, Timo},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={8110--8119},
  year={2020}
}

@article{karras2017progressive,
  title={Progressive growing of gans for improved quality, stability, and variation},
  author={Karras, Tero and Aila, Timo and Laine, Samuli and Lehtinen, Jaakko},
  journal={arXiv preprint arXiv:1710.10196},
  year={2017}
}

@inproceedings{razavi2019generating,
  title={Generating diverse high-fidelity images with vq-vae-2},
  author={Razavi, Ali and van den Oord, Aaron and Vinyals, Oriol},
  booktitle={Advances in neural information processing systems},
  pages={14866--14876},
  year={2019}
}


@article{kingma2018glow,
  title={Glow: Generative flow with invertible 1x1 convolutions},
  author={Kingma, Diederik P and Dhariwal, Prafulla},
  journal={arXiv preprint arXiv:1807.03039},
  year={2018}
}

@article{scarselli2008graph,
  title={The graph neural network model},
  author={Scarselli, Franco and Gori, Marco and Tsoi, Ah Chung and Hagenbuchner, Markus and Monfardini, Gabriele},
  journal={IEEE transactions on neural networks},
  volume={20},
  number={1},
  pages={61--80},
  year={2008},
  publisher={IEEE}
}

@inproceedings{gori2005new,
  title={A new model for learning in graph domains},
  author={Gori, Marco and Monfardini, Gabriele and Scarselli, Franco},
  booktitle={Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.},
  volume={2},
  pages={729--734},
  year={2005},
  organization={IEEE}
}

@inproceedings{singh2020don,
  title={Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias},
  author={Singh, Krishna Kumar and Mahajan, Dhruv and Grauman, Kristen and Lee, Yong Jae and Feiszli, Matt and Ghadiyaram, Deepti},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={11070--11078},
  year={2020}
}

@inproceedings{knyazev2019image,
  author = {Boris Knyazev and Xiao Lin and Mohamed R. Amer and Graham W. Taylor},
  title = {Image Classification with Hierarchical Multigraph Networks},
  booktitle = {British Machine Vision Conference (BMVC)},
  year = 2019,
  pdf = {https://arxiv.org/abs/1907.09000}
}

@article{knyazev2021LDG,
    doi = {10.1371/journal.pone.0247936},
    author = {Knyazev, Boris AND Augusta, Carolyn AND Taylor, Graham W.},
    journal = {PLOS ONE},
    publisher = {Public Library of Science},
    title = {Learning Temporal Attention in Dynamic Graphs with Bilinear Interactions},
    year = {2021},
    month = {03},
    volume = {16},
    url = {https://doi.org/10.1371/journal.pone.0247936},
    pages = {1-18},
    number = {3},
}

@inproceedings{knyazev2019understanding,
  title={Understanding Attention and Generalization in Graph Neural Networks},
  author={Knyazev, Boris and Taylor, Graham W and Amer, Mohamed},
  booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
  pages={4204--4214},
  year={2019}
}

@article{knyazev2020graph,
  title={Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation},
  author={Knyazev, Boris and de Vries, Harm and Cangea, C{\u{a}}t{\u{a}}lina and Taylor, Graham W and Courville, Aaron and Belilovsky, Eugene},
  journal={British Machine Vision Conference (BMVC) },
  year={2020}
}

@inproceedings{knyazev2020generative,
  title={Generative Compositional Augmentations for Scene Graph Prediction},
  author={Boris Knyazev and Harm de Vries and Cătălina Cangea and Graham W. Taylor and Aaron Courville and Eugene Belilovsky},
  booktitle={International Conference on Computer Vision (ICCV)},
  pdf={https://arxiv.org/abs/2007.05756},
  year={2021}
}

@inproceedings{lu2021context,
  title={Context-aware Scene Graph Generation with Seq2Seq Transformers},
  author={Lu, Yichao and Rai, Himanshu and Chang, Jason and Knyazev, Boris and Yu, Guangwei and Shekhar, Shashank and Taylor, Graham W and Volkovs, Maksims},
  booktitle={International Conference on Computer Vision (ICCV)},
  pages={15931--15941},
  year={2021}
}

@inproceedings{chung2021brick,
  title={Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning},
  author={Chung, Hyunsoo and Kim, Jungtaek and Knyazev, Boris and Lee, Jinhwi and Taylor, Graham W and Park, Jaesik and Cho, Minsu},
  booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
  year={2021}
}

@inproceedings{chen2020simple,
  title={A simple framework for contrastive learning of visual representations},
  author={Chen, Ting and Kornblith, Simon and Norouzi, Mohammad and Hinton, Geoffrey},
  booktitle={International conference on machine learning},
  pages={1597--1607},
  year={2020},
  organization={PMLR}
}

@inproceedings{verma2021towards,
  title={Towards domain-agnostic contrastive learning},
  author={Verma, Vikas and Luong, Thang and Kawaguchi, Kenji and Pham, Hieu and Le, Quoc},
  booktitle={International Conference on Machine Learning},
  pages={10530--10541},
  year={2021},
  organization={PMLR}
}

@inproceedings{hendrycks2021natural,
  title={Natural adversarial examples},
  author={Hendrycks, Dan and Zhao, Kevin and Basart, Steven and Steinhardt, Jacob and Song, Dawn},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={15262--15271},
  year={2021}
}

@article{JMLR:v17:15-239,
  author  = {Yaroslav Ganin and Evgeniya Ustinova and Hana Ajakan and Pascal Germain and Hugo Larochelle and Fran{\c{c}}ois Laviolette and Mario March and Victor Lempitsky},
  title   = {Domain-Adversarial Training of Neural Networks},
  journal = {Journal of Machine Learning Research},
  year    = {2016},
  volume  = {17},
  number  = {59},
  pages   = {1-35},
  url     = {http://jmlr.org/papers/v17/15-239.html}
}

@article{ajakan2014domain,
  title={Domain-adversarial neural networks},
  author={Ajakan, Hana and Germain, Pascal and Larochelle, Hugo and Laviolette, Fran{\c{c}}ois and Marchand, Mario},
  journal={arXiv preprint arXiv:1412.4446},
  year={2014}
}

@inproceedings{kim2020find,
	title={How to find your friendly neighborhood: Graph attention design with self-supervision},
	author={Kim, Dongkwan and Oh, Alice},
	booktitle={International Conference on Learning Representations},
	year={2020}
}

@article{vincent2021online,
	title={Online Graph Dictionary Learning},
	author={Vincent-Cuaz, C{\'e}dric and Vayer, Titouan and Flamary, R{\'e}mi and Corneli, Marco and Courty, Nicolas},
	journal={arXiv preprint arXiv:2102.06555},
	year={2021}
}

@inproceedings{ma2020adaptive,
	title={Adaptive-Step Graph Meta-Learner for Few-Shot Graph Classification},
	author={Ma, Ning and Bu, Jiajun and Yang, Jieyu and Zhang, Zhen and Yao, Chengwei and Yu, Zhi and Zhou, Sheng and Yan, Xifeng},
	booktitle={Proceedings of the 29th ACM International Conference on Information \& Knowledge Management},
	pages={1055--1064},
	year={2020}
}

@inproceedings{wang2020haar,
	title={Haar graph pooling},
	author={Wang, Yu Guang and Li, Ming and Ma, Zheng and Montufar, Guido and Zhuang, Xiaosheng and Fan, Yanan},
	booktitle={International conference on machine learning},
	pages={9952--9962},
	year={2020},
	organization={PMLR}
}

@inproceedings{garg2020generalization,
	title={Generalization and representational limits of graph neural networks},
	author={Garg, Vikas and Jegelka, Stefanie and Jaakkola, Tommi},
	booktitle={International Conference on Machine Learning},
	pages={3419--3430},
	year={2020},
	organization={PMLR}
}

@article{ji2020hopgat,
	title={Hopgat: Hop-aware supervision graph attention networks for sparsely labeled graphs},
	author={Ji, Chaojie and Wang, Ruxin and Zhu, Rongxiang and Cai, Yunpeng and Wu, Hongyan},
	journal={arXiv preprint arXiv:2004.04333},
	year={2020}
}

@article{velivckovic2019neural,
	title={Neural execution of graph algorithms},
	author={Veli{\v{c}}kovi{\'c}, Petar and Ying, Rex and Padovano, Matilde and Hadsell, Raia and Blundell, Charles},
	journal={arXiv preprint arXiv:1910.10593},
	year={2019}
}

@inproceedings{verma2019stability,
	title={Stability and generalization of graph convolutional neural networks},
	author={Verma, Saurabh and Zhang, Zhi-Li},
	booktitle={Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining},
	pages={1539--1548},
	year={2019}
}

@article{sinha2020evaluating,
	title={Evaluating logical generalization in graph neural networks},
	author={Sinha, Koustuv and Sodhani, Shagun and Pineau, Joelle and Hamilton, William L},
	journal={arXiv preprint arXiv:2003.06560},
	year={2020}
}

@inproceedings{liu2021fully,
  title={Fully Convolutional Scene Graph Generation},
  author={Liu, Hengyue and Yan, Ning and Mortazavi, Masood and Bhanu, Bir},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={11546--11556},
  year={2021}
}

@inproceedings{yehudai2021local,
	title={From local structures to size generalization in graph neural networks},
	author={Yehudai, Gilad and Fetaya, Ethan and Meirom, Eli and Chechik, Gal and Maron, Haggai},
	booktitle={International Conference on Machine Learning},
	pages={11975--11986},
	year={2021},
	organization={PMLR}
}

@article{bevilacqua2021size,
	title={Size-Invariant Graph Representations for Graph Classification Extrapolations},
	author={Bevilacqua, Beatrice and Zhou, Yangze and Ribeiro, Bruno},
	journal={arXiv preprint arXiv:2103.05045},
	year={2021}
}

@article{cobbe2021training,
	title={Training Verifiers to Solve Math Word Problems},
	author={Cobbe, Karl and Kosaraju, Vineet and Bavarian, Mohammad and Hilton, Jacob and Nakano, Reiichiro and Hesse, Christopher and Schulman, John},
	journal={arXiv preprint arXiv:2110.14168},
	year={2021}
}


@article{michaelis2019benchmarking,
	title={Benchmarking robustness in object detection: Autonomous driving when winter is coming},
	author={Michaelis, Claudio and Mitzkus, Benjamin and Geirhos, Robert and Rusak, Evgenia and Bringmann, Oliver and Ecker, Alexander S and Bethge, Matthias and Brendel, Wieland},
	journal={arXiv preprint arXiv:1907.07484},
	year={2019}
}

@article{shen2021towards,
	title={Towards out-of-distribution generalization: A survey},
	author={Shen, Zheyan and Liu, Jiashuo and He, Yue and Zhang, Xingxuan and Xu, Renzhe and Yu, Han and Cui, Peng},
	journal={arXiv preprint arXiv:2108.13624},
	year={2021}
}

@inproceedings{chen2021robust,
	title={Robust and accurate object detection via adversarial learning},
	author={Chen, Xiangning and Xie, Cihang and Tan, Mingxing and Zhang, Li and Hsieh, Cho-Jui and Gong, Boqing},
	booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
	pages={16622--16631},
	year={2021}
}

@article{li2020shape,
	title={Shape-texture debiased neural network training},
	author={Li, Yingwei and Yu, Qihang and Tan, Mingxing and Mei, Jieru and Tang, Peng and Shen, Wei and Yuille, Alan and Xie, Cihang},
	journal={arXiv preprint arXiv:2010.05981},
	year={2020}
}

@article{ahmed2020democratization,
	title={The de-democratization of ai: Deep learning and the compute divide in artificial intelligence research},
	author={Ahmed, Nur and Wahed, Muntasir},
	journal={arXiv preprint arXiv:2010.15581},
	year={2020}
}

@inproceedings{abdalla2021grey,
	title={The Grey Hoodie Project: Big tobacco, big tech, and the threat on academic integrity},
	author={Abdalla, Mohamed and Abdalla, Moustafa},
	booktitle={Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society},
	pages={287--297},
	year={2021}
}

@article{scholkopf2021toward,
	title={Toward causal representation learning},
	author={Sch{\"o}lkopf, Bernhard and Locatello, Francesco and Bauer, Stefan and Ke, Nan Rosemary and Kalchbrenner, Nal and Goyal, Anirudh and Bengio, Yoshua},
	journal={Proceedings of the IEEE},
	volume={109},
	number={5},
	pages={612--634},
	year={2021},
	publisher={IEEE}
}

@article{zhou2021domain,
	title={Domain generalization: A survey},
	author={Zhou, Kaiyang and Liu, Ziwei and Qiao, Yu and Xiang, Tao and Loy, Chen Change},
	journal={arXiv preprint arXiv:2103.02503},
	year={2021}
}

@inproceedings{knyazev2021parameter,
  title={Parameter Prediction for Unseen Deep Architectures},
  author={Knyazev, Boris and Drozdzal, Michal and Taylor, Graham W and Romero-Soriano, Adriana},
  booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
  year={2021}  
}

@article{hamilton2018embedding,
  title={Embedding logical queries on knowledge graphs},
  author={Hamilton, William L and Bajaj, Payal and Zitnik, Marinka and Jurafsky, Dan and Leskovec, Jure},
  journal={arXiv preprint arXiv:1806.01445},
  year={2018}
}

@article{zhou2020graph,
  title={Graph neural networks: A review of methods and applications},
  author={Zhou, Jie and Cui, Ganqu and Hu, Shengding and Zhang, Zhengyan and Yang, Cheng and Liu, Zhiyuan and Wang, Lifeng and Li, Changcheng and Sun, Maosong},
  journal={AI Open},
  volume={1},
  pages={57--81},
  year={2020},
  publisher={Elsevier}
}

@article{wu2021graph,
  title={Graph Neural Networks for Natural Language Processing: A Survey},
  author={Wu, Lingfei and Chen, Yu and Shen, Kai and Guo, Xiaojie and Gao, Hanning and Li, Shucheng and Pei, Jian and Long, Bo},
  journal={arXiv preprint arXiv:2106.06090},
  year={2021}
}

@article{jain2017non,
  title={Non-convex optimization for machine learning},
  author={Jain, Prateek and Kar, Purushottam},
  journal={arXiv preprint arXiv:1712.07897},
  year={2017}
}

@article{radford2021learning,
  title={Learning transferable visual models from natural language supervision},
  author={Radford, Alec and Kim, Jong Wook and Hallacy, Chris and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela and Clark, Jack and others},
  journal={arXiv preprint arXiv:2103.00020},
  year={2021}
}