Skip to content
Branch: master
Find file History
Latest commit bf3994e Jul 2, 2019

Hierarchical Graph Representation Learning with Differentiable Pooling

Paper link:

Author's code repo:

This folder contains a DGL implementation of the DiffPool model. The first pooling layer is computed with DGL, and following pooling layers are computed with tensorized operation since the pooled graphs are dense.


  • PyTorch 1.0+

How to run

python --dataset ENZYMES --pool_ratio 0.10 --num_pool 1
python --dataset DD --pool_ratio 0.15 --num_pool 1  


ENZYMES 63.33% (with early stopping) DD 79.31% (with early stopping)


You can’t perform that action at this time.