Skip to content

Commit

Permalink
[Example] Graph Random Neural Network (dmlc#2502)
Browse files Browse the repository at this point in the history 
* Add Implementation of GRAND

* Performance updated

* Update README.md

add indexing entries

* add indexing entries for grand

* change grand from 2021 to 2020

* [Example] fix some bugs

* [Examples] fix bug

Co-authored-by: 张恒瑞 <[email protected]>
Co-authored-by: 张恒瑞 <[email protected]>
Co-authored-by: zhjwy9343 <[email protected]>
  • Loading branch information
@hengruizhang98 @zhjwy9343
4 people authored Jan 13, 2021
1 parent 1502c56 commit 80fdcfd
Show file tree
Hide file tree
Showing 4 changed files with 456 additions and 37 deletions.
75 changes: 38 additions & 37 deletions examples/README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2,56 +2,57 @@

## Overview

| Paper | node classification | link prediction / classification | graph property prediction | sampling | OGB |
| ------------------------------------------------------------------------------------------------------------------------ | ------------------- | -------------------------------- | ------------------------- | ------------------ | ------------------ |
| [Heterogeneous Graph Transformer](#hgt) | :heavy_check_mark: | :heavy_check_mark: | | | |
| [Graph Convolutional Networks for Graphs with Multi-Dimensionally Weighted Edges](#mwe) | :heavy_check_mark: | | | | :heavy_check_mark: |
| [SIGN: Scalable Inception Graph Neural Networks](#sign) | :heavy_check_mark: | | | | :heavy_check_mark: |
| [Strategies for Pre-training Graph Neural Networks](#prestrategy) | | | :heavy_check_mark: | | |
| [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](#appnp) | :heavy_check_mark: | | | | |
| [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](#clustergcn) | :heavy_check_mark: | | | :heavy_check_mark: | :heavy_check_mark: |
| [Deep Graph Infomax](#dgi) | :heavy_check_mark: | | | | |
| [Hierarchical Graph Representation Learning with Differentiable Pooling](#diffpool) | | | :heavy_check_mark: | | |
| [Representation Learning for Attributed Multiplex Heterogeneous Network](#gatne-t) | | :heavy_check_mark: | | | |
| [How Powerful are Graph Neural Networks?](#gin) | :heavy_check_mark: | | :heavy_check_mark: | | :heavy_check_mark: |
| [Heterogeneous Graph Attention Network](#han) | :heavy_check_mark: | | | | |
| [Simplifying Graph Convolutional Networks](#sgc) | :heavy_check_mark: | | | | |
| [Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective](#mgcn) | | | :heavy_check_mark: | | |
| Paper | node classification | link prediction / classification | graph property prediction | sampling | OGB |
| ------------------------------------------------------------ | ------------------- | -------------------------------- | ------------------------- | ------------------ | ------------------ |
| [Graph Random Neural Network for Semi-Supervised Learning on Graphs](#grand) | :heavy_check_mark: | | | | |
| [Heterogeneous Graph Transformer](#hgt) | :heavy_check_mark: | :heavy_check_mark: | | | |
| [Graph Convolutional Networks for Graphs with Multi-Dimensionally Weighted Edges](#mwe) | :heavy_check_mark: | | | | :heavy_check_mark: |
| [SIGN: Scalable Inception Graph Neural Networks](#sign) | :heavy_check_mark: | | | | :heavy_check_mark: |
| [Strategies for Pre-training Graph Neural Networks](#prestrategy) | | | :heavy_check_mark: | | |
| [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](#appnp) | :heavy_check_mark: | | | | |
| [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](#clustergcn) | :heavy_check_mark: | | | :heavy_check_mark: | :heavy_check_mark: |
| [Deep Graph Infomax](#dgi) | :heavy_check_mark: | | | | |
| [Hierarchical Graph Representation Learning with Differentiable Pooling](#diffpool) | | | :heavy_check_mark: | | |
| [Representation Learning for Attributed Multiplex Heterogeneous Network](#gatne-t) | | :heavy_check_mark: | | | |
| [How Powerful are Graph Neural Networks?](#gin) | :heavy_check_mark: | | :heavy_check_mark: | | :heavy_check_mark: |
| [Heterogeneous Graph Attention Network](#han) | :heavy_check_mark: | | | | |
| [Simplifying Graph Convolutional Networks](#sgc) | :heavy_check_mark: | | | | |
| [Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective](#mgcn) | | | :heavy_check_mark: | | |
| [Pushing the Boundaries of Molecular Representation for Drug Discovery with the Graph Attention Mechanism](#attentivefp) | | | :heavy_check_mark: | | |
| [MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing](#mixhop) | :heavy_check_mark: | | | | |
| [Graph Attention Networks](#gat) | :heavy_check_mark: | | | | :heavy_check_mark: |
| [Attention-based Graph Neural Network for Semi-supervised Learning](#agnn) | :heavy_check_mark: | | | :heavy_check_mark: | |
| [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](#pinsage) | | | | | |
| [Semi-Supervised Classification with Graph Convolutional Networks](#gcn) | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: |
| [Graph Convolutional Matrix Completion](#gcmc) | | :heavy_check_mark: | | | |
| [Inductive Representation Learning on Large Graphs](#graphsage) | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | :heavy_check_mark: |
| [metapath2vec: Scalable Representation Learning for Heterogeneous Networks](#metapath2vec) | :heavy_check_mark: | | | | |
| [Topology Adaptive Graph Convolutional Networks](#tagcn) | :heavy_check_mark: | | | | |
| [Modeling Relational Data with Graph Convolutional Networks](#rgcn) | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | |
| [Neural Message Passing for Quantum Chemistry](#mpnn) | | | :heavy_check_mark: | | |
| [SchNet: A continuous-filter convolutional neural network for modeling quantum interactions](#schnet) | | | :heavy_check_mark: | | |
| [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](#chebnet) | :heavy_check_mark: | | :heavy_check_mark: | | |
| [Geometric deep learning on graphs and manifolds using mixture model CNNs](#monet) | :heavy_check_mark: | | :heavy_check_mark: | | |
| [Molecular Graph Convolutions: Moving Beyond Fingerprints](#weave) | | | :heavy_check_mark: | | |
| [LINE: Large-scale Information Network Embedding](#line) | | :heavy_check_mark: | | | :heavy_check_mark: |
| [DeepWalk: Online Learning of Social Representations](#deepwalk) | | :heavy_check_mark: | | | :heavy_check_mark: |
| [Self-Attention Graph Pooling](#sagpool) | | | :heavy_check_mark: | | |
| [Convolutional Networks on Graphs for Learning Molecular Fingerprints](#nf) | | | :heavy_check_mark: | | |
| [MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing](#mixhop) | :heavy_check_mark: | | | | |
| [Graph Attention Networks](#gat) | :heavy_check_mark: | | | | :heavy_check_mark: |
| [Attention-based Graph Neural Network for Semi-supervised Learning](#agnn) | :heavy_check_mark: | | | :heavy_check_mark: | |
| [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](#pinsage) | | | | | |
| [Semi-Supervised Classification with Graph Convolutional Networks](#gcn) | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: |
| [Graph Convolutional Matrix Completion](#gcmc) | | :heavy_check_mark: | | | |
| [Inductive Representation Learning on Large Graphs](#graphsage) | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | :heavy_check_mark: |
| [metapath2vec: Scalable Representation Learning for Heterogeneous Networks](#metapath2vec) | :heavy_check_mark: | | | | |
| [Topology Adaptive Graph Convolutional Networks](#tagcn) | :heavy_check_mark: | | | | |
| [Modeling Relational Data with Graph Convolutional Networks](#rgcn) | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | |
| [Neural Message Passing for Quantum Chemistry](#mpnn) | | | :heavy_check_mark: | | |
| [SchNet: A continuous-filter convolutional neural network for modeling quantum interactions](#schnet) | | | :heavy_check_mark: | | |
| [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](#chebnet) | :heavy_check_mark: | | :heavy_check_mark: | | |
| [Geometric deep learning on graphs and manifolds using mixture model CNNs](#monet) | :heavy_check_mark: | | :heavy_check_mark: | | |
| [Molecular Graph Convolutions: Moving Beyond Fingerprints](#weave) | | | :heavy_check_mark: | | |
| [LINE: Large-scale Information Network Embedding](#line) | | :heavy_check_mark: | | | :heavy_check_mark: |
| [DeepWalk: Online Learning of Social Representations](#deepwalk) | | :heavy_check_mark: | | | :heavy_check_mark: |
| [Self-Attention Graph Pooling](#sagpool) | | | :heavy_check_mark: | | |
| [Convolutional Networks on Graphs for Learning Molecular Fingerprints](#nf) | | | :heavy_check_mark: | | |

## 2020

- <a name="grand"></a> Feng et al. Graph Random Neural Network for Semi-Supervised Learning on Graphs. [Paper link](https://arxiv.org/abs/2005.11079).
- Example code: [PyTorch](../examples/pytorch/grand)
- Tags: semi-supervised node classification, simplifying graph convolution, data augmentation
- <a name="hgt"></a> Hu et al. Heterogeneous Graph Transformer. [Paper link](https://arxiv.org/abs/2003.01332).
- Example code: [PyTorch](../examples/pytorch/hgt)
- Tags: dynamic heterogeneous graphs, large-scale, node classification, link prediction

- <a name="mwe"></a> Chen. Graph Convolutional Networks for Graphs with Multi-Dimensionally Weighted Edges. [Paper link](https://cims.nyu.edu/~chenzh/files/GCN_with_edge_weights.pdf).
- Example code: [PyTorch on ogbn-proteins](../examples/pytorch/ogb/ogbn-proteins)
- Tags: node classification, weighted graphs, OGB

- <a name="sign"></a> Frasca et al. SIGN: Scalable Inception Graph Neural Networks. [Paper link](https://arxiv.org/abs/2004.11198).
- Example code: [PyTorch on ogbn-arxiv/products/mag](../examples/pytorch/ogb/sign), [PyTorch](../examples/pytorch/sign)
- Tags: node classification, OGB, large-scale, heterogeneous graphs

- <a name="prestrategy"></a> Hu et al. Strategies for Pre-training Graph Neural Networks. [Paper link](https://arxiv.org/abs/1905.12265).
- Example code: [Molecule embedding](https://github.com/awslabs/dgl-lifesci/tree/master/examples/molecule_embeddings), [PyTorch for custom data](https://github.com/awslabs/dgl-lifesci/tree/master/examples/property_prediction/csv_data_configuration)
- Tags: molecules, graph classification, unsupervised learning, self-supervised learning, molecular property prediction
Expand Down
Loading

0 comments on commit 80fdcfd

Please sign in to comment.