Skip to content

Latest commit

 

History

History
48 lines (28 loc) · 2.39 KB

README.md

File metadata and controls

48 lines (28 loc) · 2.39 KB

Keras implementation of Structural Deep Network Embedding, KDD 2016

some examples

visualzing 20newsgroup data

label embedding from stackexchange.datascience (deep-learning as an example)

important scripts

main algorithm

  • core.py

experiments

20newsgroup visualization

  • 20newsgroup_train.py: train for 20newsgroup dataset
  • 20newsgroup_viz.py: visualization using sklearn.manifold.TSNE
  • 20newsgroup_tensorboard_embedding.py: produce the embedding files for tensorboard projector, which is more interactive
    • you can also play with it here using trained embeddings

link prediction

  • link_prediction.py: train (including grid search) and test

stackexchange label visualization

  • stackexchange_train.py: train for the stackexchange label cooccurence graph
  • stackexchange_label_embedding.py: produce the embedding files for tensorboard projector
    • you can also play with it here using trained embeddings

other implementations