项目文件夹

文件

T

文件历史

VoVAllen 9c790b1143 [Dataset] Add CoraFull, Amazon, KarateClub, Coauthor Dataset (#855 )

* convert np.ndarray to backend tensor

* add datasets

* add qm7

* add dataset

* add dataset

* fix

* change ppi

* tu dataset

* add datasets

* fix

* fix

* fix

* fix

* add docstring

* docs

* doc

2019-10-01 01:19:59 +08:00

model

[Model][Hotfix] DiffPool formatting fix (#696 )

2019-07-02 15:19:57 +08:00

data_utils.py

[Model][Hotfix] DiffPool formatting fix (#696 )

2019-07-02 15:19:57 +08:00

README.md

[Model] DiffPool with both DGL and tensorized operatons (#665 )

2019-07-01 20:00:15 +08:00

train.py

[Dataset] Add CoraFull, Amazon, KarateClub, Coauthor Dataset (#855 )

2019-10-01 01:19:59 +08:00

README.md

Hierarchical Graph Representation Learning with Differentiable Pooling

Paper link: https://arxiv.org/abs/1806.08804

Author's code repo: https://github.com/RexYing/diffpool

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.

Dependencies

PyTorch 1.0+

How to run

python train.py --dataset ENZYMES --pool_ratio 0.10 --num_pool 1
python train.py --dataset DD --pool_ratio 0.15 --num_pool 1

Performance

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