A (Growing) Paper List of Evolutionary Computation (EC) and Swarm Intelligence (SI) on Top-Tier Publications (e.g., Nature, Science, etc.)
This is a growing paper list for evolutionary computation (EC) and Swarm Intelligence (SI). Currently we are actively updating it (from 2021). Owing to the abundance of literatures, however, we believe that many interesting works are still missed here. If you find them missed here, welcome to contact with us via Issues or Pull requests to add. Recently (2023), we have noticed that some other research group(s) also starts to adopt a similar way to collect literatures regarding EC, which is a good news.
NOTE: Although our initial goal was to cover only parallel and distributed EC, now our focus is switched to Evolutionary Computation (EC) researches and applications for (>30) chosen journals and conferences (such as Nature, Science, PNAS (Proceedings of the National Academy of Sciences), PRL (Physical Review Letters), JACS, PIEEE, Nature Physics, Nature Chemistry, Nature Materials, Nature Genetics, Nature Neuroscience, Nature Geoscience, Nature Photonics, Nature Nanotechnology, Nature Sustainability, Nature Human Behaviour, Nature Ecology & Evolution, Nature Communications, Science Robotics, JACM (Journal of the ACM), CACM (Communications of the ACM), FOCS (IEEE Annual Symposium on Foundations of Computer Science), JMLR (Journal of Machine Learning Research), AIJ (Artificial Intelligence Journal), NeurIPS (Neural Information Processing Systems), ICML (International Conference on Machine Learning), etc.) besides EC-specific publications (e.g., ECJ/IEEE-TEVC/ACM-TELO/ACM-FOGA/PPSN/ACM-GECCO/IEEE-CEC/...). For EC-focused publications, currently still only Parallel/Distributed EC are covered. The total number of journals and conferences chosen in this repository are still considered to increase in the future given that now only a subset is added here (sorry for this).
WARNING: In this paper repository, we do NOT judge the scientific(theoretical)/engineering(practical) value of each paper, since such a value judgement is often a non-trival task. Instead, we ONLY provide a widely-accessible platform to collect papers regarding EC on some (rather all) top-tier and also related EC-focused journals as much as possible. Since only PDEC are covered for EC-focused publications, this paper collection may be somewhat biased, which should be noticed.
"Responsible for adaptation, optimization, and innovation in the living world, evolution executes a simple algorithm of diversifcation and natural selection, an algorithm that works at all levels of complexity from single protein molecules to whole ecosystems."---Nobel Lecture, by Frances H. Arnold, California Institute of Technology
Here, we consider a family of evolutionary algorithms (and also several closely-related techniques, e.g. random search and simulated annealing). Since initially we focused primarily on their parallel/distributed versions and variants, we provide a reference list for their original / seminal / landmark / survey / review / opinion papers, in order to help better understand them (especially for newcomers). We strongly suggest to see e.g. 2015's Review paper in Nature or 1993's Review paper in Science.
- Four Conventional EAs
- Genetic Algorithms (GA)
- Evolution Strategies (ES) [ applications ]
- Covariance Matrix Adaptation ES (CMA-ES)
- Evolutionary Programming (EP)
- Genetic Programming (GP)
- Two Swarm Intelligence (SI) Siblings
- Evolutionary Multi-Objective Optimization (EMO) Frameworks
- Several Relatively New Extensions/Improvements/Variants
- Co-Evolutionary Algorithms (CEA)
- Differential Evolution (DE)
- Memetic Algorithms (MA)
- Estimation of Distribution Algorithms (EDA)
- Natural Evolution Strategies (NES)
- Quality-Diversity (QD)
- Multidimensional Archive of Phenotypic Elites (MAP-Elites)
- NeuroEvolution (aka Evolving Neural Networks)
- Evolutionary/Swarm Robotics (ER/SR)
- Artificial Life (AL)
- Open-Ended Evolution
- Common Individual-based Counterparts/Baselines/Competitors (especially for their stochastic versions)
- Random Search (RS)
- Local Search (LS) / Hill Climbers (HC)
- Simulated Annealing (SA)
- Tabu Search (TS)
"Frequently nonadditive interaction (i.e., "epistasis" or "nonlinearity") makes it impossible to determine the performance of a structure from a study of its isolated parts. While these difficulties pose a real problem for the analyst, we know that they are routinely handled by biological adaptive processes, qua processes."---[John H. Holland, Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence, 1992]
This ongoing paper list for EC/SI (previous only for PDEC) was supported by Shenzhen Fundamental Research Program under Grant No. JCYJ20200109141235597 (2,000,000 Yuan from 2021 to 2023). Now it is supported by National Natural Science Foundation of China under Grant No. 72401122, Guangdong Basic and Applied Basic Research Foundation under Grant No. 2024A1515012241 and 2021A1515110024. We also acknowledge the early contribution from Vincent A. Cicirello. We thank e.g., link (from a PhD candidate of Tsinghua) to this (unbiased as much as possible) paper-summary project.
Currently, this long-term project is led by Qiqi Duan @ SUSTech, Shenzhen, China (just a fan of both biological and computational evolution, published in some of top-tier and/or representative journals and conferences such as JMLR (CCF-A), TPDS (CCF-A), TMLR, TEVC (CCF-B), PPSN (CCF-B), GECCO (CCF-C), ASOC (JCR-1), CEC, SSCI, etc.), with the following kindly collaborators:
- Yuwei Huang (evolutionary reinforcement learning)
- Lijun Sun (swarm intelligence and swarm robotics)
- Yajing Tan (swarm intelligence for large language models)
- Xingyu Zhou (evolutionary computation for machine learning)