[WSDM 2021]Bipartite Graph Embedding via Mutual Information Maximization
-
Updated
Jul 6, 2021 - Python
[WSDM 2021]Bipartite Graph Embedding via Mutual Information Maximization
Chainer implementation of deep-INFOMAX
Deriving Generative Classifier From Any Given Discriminative Classifier
Evaluation of multiple graph neural network models—GCN, GAT, GraphSAGE, MPNN and DGI—for node classification on graph-structured data. Preprocessing includes feature normalization and adjacency-matrix regularization, and an ensemble of model predictions boosts performance. The best ensemble achieves 83.47% test accuracy.
Add a description, image, and links to the deep-infomax topic page so that developers can more easily learn about it.
To associate your repository with the deep-infomax topic, visit your repo's landing page and select "manage topics."