README.md

Official DGL Examples and Modules

The folder contains example implementations of selected research papers related to Graph Neural Networks. Note that the examples may not work with incompatible DGL versions.

• For examples working with the latest master (or the latest nightly build), check out https://github.com/dmlc/dgl/tree/master/examples.
• For examples working with a certain release, check out https://github.com/dmlc/dgl/tree/<release_version>/examples (E.g., https://github.com/dmlc/dgl/tree/0.5.x/examples)

To quickly locate the examples of your interest, search for the tagged keywords or use the search tool on dgl.ai.

2022

• Balin et al. Layer-Neighbor Sampling -- Defusing Neighborhood Explosion in GNNs. Paper link
  • Example code: PyTorch
  • Tags: node classification, weighted graphs, sampling

2021

• Mallet et al. Learning Protein and Small Molecule binding sites in RNA molecules with 2.5D graphs. Paper link
  • Example code: PyTorch
  • Tags: semi-supervised node classification
• Xing et al. Learning Hierarchical Graph Neural Networks for Image Clustering.
  • Example code: PyTorch
  • Tags: clustering
• Ivanov et al. Boost then Convolve: Gradient Boosting Meets Graph Neural Networks. Paper link.
  • Example code: PyTorch
  • Tags: semi-supervised node classification, tabular data, GBDT
• Huang et al. Combining Label Propagation and Simple Models Out-performs Graph Neural Networks. Paper link.
  • Example code: PyTorch
  • Tags: efficiency, node classification, label propagation
• Zhao et al. Point Transformer. Paper link.
  • Example code: PyTorch
  • Tags: point cloud classification, point cloud part-segmentation
• Guo et al. PCT: Point cloud transformer. Paper link.
  • Example code: PyTorch
  • Tags: point cloud classification, point cloud part-segmentation
• Brody et al. How Attentive are Graph Attention Networks? Paper link.
  • Example code: PyTorch
  • Tags: graph attention, gat, gatv2, attention
• Thakoor et al. Large-Scale Representation Learning on Graphs via Bootstrapping. Paper link.
  • Example code: PyTorch
  • Tags: contrastive learning for node classification.
• Bouritsas et al. Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting. Paper link.
  • Example code: PyTorch
  • Tags: subgraph isomorphism counting, graph classification.
• Song et al. Network In Graph Neural Network. Paper link.
  • Example code: PyTorch
  • Tags: model-agnostic methodology, link prediction, open graph benchmark.
• Qin et al. BiPointNet: Binary Neural Network for Point Clouds. Paper link
  • Example code: PyTorch
  • Tags: point cloud classification, network binarization.

2020

• Wagh et al. EEG-GCNN: Augmenting Electroencephalogram-based Neurological Disease Diagnosis using a Domain-guided Graph Convolutional Neural Network. Paper link.

  • Example code: PyTorch
  • Tags: graph classification, eeg representation learning, brain activity, graph convolution, neurological disease classification, large dataset, edge weights, node features, fully-connected graph, graph neural network

• Wang et al. Network Embedding with Completely-imbalanced Labels. Paper link.

  • Example code: PyTorch
  • Tags: node classification, network embedding, completely-imbalanced labels

• Hassani and Khasahmadi. Contrastive Multi-View Representation Learning on Graphs. Paper link.

  • Example code: PyTorch
  • Tags: graph diffusion, self-supervised learning

• Zhu et al. Deep Graph Contrastive Representation Learning. Paper link.

  • Example code: PyTorch
  • Tags: contrastive learning for node classification.

• Feng et al. Graph Random Neural Network for Semi-Supervised Learning on Graphs. Paper link.

  • Example code: PyTorch
  • Tags: semi-supervised node classification, simplifying graph convolution, data augmentation

• Hu et al. Heterogeneous Graph Transformer. Paper link.

  • Example code: PyTorch
  • Tags: dynamic heterogeneous graph, large-scale, node classification, link prediction

• Chen. Graph Convolutional Networks for Graphs with Multi-Dimensionally Weighted Edges. Paper link.

  • Example code: PyTorch on ogbn-proteins
  • Tags: node classification, weighted graphs, OGB

• Frasca et al. SIGN: Scalable Inception Graph Neural Networks. Paper link.

  • Example code: PyTorch on ogbn-arxiv/products/mag, PyTorch
  • Tags: node classification, OGB, large-scale, heterogeneous graph

• Hu et al. Strategies for Pre-training Graph Neural Networks. Paper link.

  • Example code: Molecule embedding, PyTorch for custom data
  • Tags: molecules, graph classification, unsupervised learning, self-supervised learning, molecular property prediction

• Marc Brockschmidt. GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation. Paper link.

  • Example code: PyTorch
  • Tags: multi-relational graphs, hypernetworks, GNN architectures

• Li, Maosen, et al. Graph Cross Networks with Vertex Infomax Pooling. Paper link.

  • Example code: PyTorch
  • Tags: pooling, graph classification

• Liu et al. Towards Deeper Graph Neural Networks. Paper link.

  • Example code: PyTorch
  • Tags: over-smoothing, node classification

• Klicpera et al. Directional Message Passing for Molecular Graphs. Paper link.

  • Example code: PyTorch
  • Tags: molecules, molecular property prediction, quantum chemistry

• Rossi et al. Temporal Graph Networks For Deep Learning on Dynamic Graphs. Paper link.

  • Example code: Pytorch
  • Tags: temporal, node classification

• Vashishth, Shikhar, et al. Composition-based Multi-Relational Graph Convolutional Networks. Paper link.

  • Example code: PyTorch
  • Tags: multi-relational graphs, graph neural network

• Li et al. DeeperGCN: All You Need to Train Deeper GCNs. Paper link.

  • Example code: PyTorch
  • Tags: over-smoothing, deeper gnn, OGB

• Bi, Ye, et al. A Heterogeneous Information Network based Cross DomainInsurance Recommendation System for Cold Start Users. Paper link.

  • Example code: Pytorch
  • Tags: cross-domain recommendation, graph neural network

• Fu X, Zhang J, Meng Z, et al. MAGNN: metapath aggregated graph neural network for heterogeneous graph embedding. Paper link.

  • Example code: OpenHGNN
  • Tags: Heterogeneous graph, Graph neural network, Graph embedding

• Zhao J, Wang X, et al. Network Schema Preserving Heterogeneous Information Network Embedding. Paper link.

  • Example code: OpenHGNN
  • Tags: Heterogeneous graph, Graph neural network, Graph embedding, Network Schema

• Dou Y, Liu Z, et al. Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters. Paper link.

  • Example code: PyTorch
  • Tags: Multi-relational graph, Graph neural network, Fraud detection, Reinforcement learning, Node classification

• Zhang et al. Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning. Paper link.

  • Example code: PyTorch
  • Tags: link prediction, labeling trick, OGB

2019

• Sun et al. InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization. Paper link.
  • Example code: PyTorch
  • Tags: semi-supervised graph regression, unsupervised graph classification
• Bianchi et al. Graph Neural Networks with Convolutional ARMA Filters. Paper link.
  • Example code: PyTorch
  • Tags: node classification
• Klicpera et al. Predict then Propagate: Graph Neural Networks meet Personalized PageRank. Paper link.
  • Example code: PyTorch, MXNet
  • Tags: node classification
• Chiang et al. Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks. Paper link.
  • Example code: PyTorch, PyTorch-based GraphSAGE variant on OGB, PyTorch-based GAT variant on OGB
  • Tags: graph partition, node classification, large-scale, OGB, sampling
• Veličković et al. Deep Graph Infomax. Paper link.
  • Example code: PyTorch, TensorFlow
  • Tags: unsupervised learning, node classification
• Ying et al. Hierarchical Graph Representation Learning with Differentiable Pooling. Paper link.
  • Example code: PyTorch
  • Tags: pooling, graph classification, graph coarsening
• Cen et al. Representation Learning for Attributed Multiplex Heterogeneous Network. Paper link.
  • Example code: PyTorch
  • Tags: heterogeneous graph, link prediction, large-scale
• Xu et al. How Powerful are Graph Neural Networks? Paper link.
  • Example code: PyTorch on graph classification, PyTorch on node classification, PyTorch on ogbg-ppa, MXNet
  • Tags: graph classification, node classification, OGB
• Koncel-Kedziorski et al. Text Generation from Knowledge Graphs with Graph Transformers. Paper link.
  • Example code: PyTorch
  • Tags: knowledge graph, text generation
• Wang et al. Heterogeneous Graph Attention Network. Paper link.
  • Example code: PyTorch, OpenHGNN
  • Tags: heterogeneous graph, node classification
• Chen et al. Supervised Community Detection with Line Graph Neural Networks. Paper link.
  • Example code: PyTorch
  • Tags: line graph, community detection
• Wu et al. Simplifying Graph Convolutional Networks. Paper link.
  • Example code: PyTorch, MXNet
  • Tags: node classification
• Wang et al. Dynamic Graph CNN for Learning on Point Clouds. Paper link.
  • Example code: PyTorch
  • Tags: point cloud classification
• Zhang et al. Graphical Contrastive Losses for Scene Graph Parsing. Paper link.
  • Example code: MXNet
  • Tags: scene graph extraction
• Lee et al. Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks. Paper link.
  • Pooling module: PyTorch encoder, PyTorch decoder
  • Tags: graph classification
• Coley et al. A graph-convolutional neural network model for the prediction of chemical reactivity. Paper link.
  • Example code: PyTorch
  • Tags: molecules, reaction prediction
• Lu et al. Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective. Paper link.
  • Example code: PyTorch
  • Tags: molecules, quantum chemistry
• Xiong et al. Pushing the Boundaries of Molecular Representation for Drug Discovery with the Graph Attention Mechanism. Paper link.
  • Example code: PyTorch (with attention visualization), PyTorch for custom data
  • Tags: molecules, molecular property prediction
• Sun et al. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space. Paper link.
  • Example code: PyTorch, PyTorch for custom data
  • Tags: knowledge graph
• Abu-El-Haija et al. MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing. Paper link.
  • Example code: PyTorch
  • Tags: node classification
• Lee, Junhyun, et al. Self-Attention Graph Pooling. Paper link.
  • Example code: PyTorch
  • Tags: graph classification, pooling
• Zhang, Zhen, et al. Hierarchical Graph Pooling with Structure Learning. Paper link.
  • Example code: PyTorch
  • Tags: graph classification, pooling
• Gao, Hongyang, et al. Graph Representation Learning via Hard and Channel-Wise Attention Networks Paper link.
  • Example code: PyTorch
  • Tags: node classification, graph attention
• Wang, Xiang, et al. Neural Graph Collaborative Filtering. Paper link.
  • Example code: PyTorch
  • Tags: Collaborative Filtering, recommender system, Graph Neural Network
• Ying, Rex, et al. GNNExplainer: Generating Explanations for Graph Neural Networks. Paper link.
  • Example code: PyTorch
  • Tags: Graph Neural Network, Explainability
• Zhang C, Song D, et al. Heterogeneous graph neural network. Paper link.
  • Example code: OpenHGNN
  • Tags: Heterogeneous graph, Graph neural network, Graph embedding
• Yun S, Jeong M, et al. Graph transformer networks. Paper link.
  • Example code: OpenHGNN
  • Tags: Heterogeneous graph, Graph neural network, Graph structure
• Li A, Qin Z, et al. Spam Review Detection with Graph Convolutional Networks. Paper link.
  • Example code: PyTorch
  • Tags: Fraud detection, Heterogeneous graph, Edge classification, Graph attention
• Liu Z, et al. Geniepath: Graph neural networks with adaptive receptive paths. Paper link.
  • Example code: PyTorch
  • Tags: Fraud detection, Node classification, Graph attention, LSTM, Adaptive receptive fields
• You J, et al. Position-aware graph neural networks. Paper link.
  • Example code: PyTorch
  • Tags: Positional encoding, Link prediction, Link-pair prediction

2018

• Li et al. Learning Deep Generative Models of Graphs. Paper link.

  • Example code: PyTorch example for cycles, PyTorch example for molecules
  • Tags: generative models, autoregressive models, molecules

• Veličković et al. Graph Attention Networks. Paper link.

  • Example code: PyTorch, PyTorch on ogbn-arxiv, PyTorch on ogbn-products, TensorFlow, MXNet
  • Tags: node classification, OGB

• Jin et al. Junction Tree Variational Autoencoder for Molecular Graph Generation. Paper link.

  • Example code: PyTorch
  • Tags: generative models, molecules, VAE

• Thekumparampil et al. Attention-based Graph Neural Network for Semi-supervised Learning. Paper link.

  • Example code: PyTorch
  • Tags: node classification

• Ying et al. Graph Convolutional Neural Networks for Web-Scale Recommender Systems. Paper link.

  • Example code: PyTorch
  • Tags: recommender system, large-scale, sampling

• Berg Palm et al. Recurrent Relational Networks. Paper link.

  • Example code: PyTorch
  • Tags: sudoku solving

• Yu et al. Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting. Paper link.

  • Example code: PyTorch
  • Tags: spatio-temporal, traffic forecasting

• Zhang et al. An End-to-End Deep Learning Architecture for Graph Classification. Paper link.

  • Pooling module: PyTorch, TensorFlow, MXNet
  • Tags: graph classification

• Zhang et al. Link Prediction Based on Graph Neural Networks. Paper link.

  • Example code: PyTorch
  • Tags: link prediction, sampling

• Xu et al. Representation Learning on Graphs with Jumping Knowledge Networks. Paper link.

  • Example code: PyTorch
  • Tags: message passing, neighborhood

• Zhang et al. GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs. Paper link.

  • Example code: pytorch
  • Tags: Static discrete temporal graph, traffic forecasting

• Feng et al. Hypergraph Neural Networks. Paper link.

  • Example code: pytorch
  • Tags: hypergraph

2017

• Kipf and Welling. Semi-Supervised Classification with Graph Convolutional Networks. Paper link.

  • Example code: PyTorch, PyTorch on ogbn-arxiv, PyTorch on ogbl-ppa, PyTorch on ogbg-ppa, TensorFlow, MXNet
  • Tags: node classification, link prediction, graph classification, OGB

• Sabour et al. Dynamic Routing Between Capsules. Paper link.

  • Example code: PyTorch
  • Tags: image classification

• van den Berg et al. Graph Convolutional Matrix Completion. Paper link.

  • Example code: PyTorch
  • Tags: matrix completion, recommender system, link prediction, bipartite graphs

• Hamilton et al. Inductive Representation Learning on Large Graphs. Paper link.

  • Example code: PyTorch, PyTorch on ogbn-products, PyTorch on ogbn-mag, PyTorch on ogbl-ppa, MXNet
  • Tags: node classification, sampling, unsupervised learning, link prediction, OGB

• Dong et al. metapath2vec: Scalable Representation Learning for Heterogeneous Networks. Paper link.

  • Example code: PyTorch
  • Tags: heterogeneous graph, network embedding, large-scale, node classification

• Du et al. Topology Adaptive Graph Convolutional Networks. Paper link.

  • Example code: PyTorch, MXNet
  • Tags: node classification

• Qi et al. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Paper link.

  • Example code: PyTorch
  • Tags: point cloud classification, point cloud part-segmentation

• Qi et al. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. Paper link.

  • Example code: PyTorch
  • Tags: point cloud classification

• Schlichtkrull. Modeling Relational Data with Graph Convolutional Networks. Paper link.

  • Example code: PyTorch example using homogeneous DGLGraphs, PyTorch, TensorFlow, MXNet
  • Tags: node classification, link prediction, heterogeneous graph, sampling

• Vaswani et al. Attention Is All You Need. Paper link.

  • Example code: PyTorch
  • Tags: machine translation

• Gilmer et al. Neural Message Passing for Quantum Chemistry. Paper link.

  • Example code: PyTorch, PyTorch for custom data
  • Tags: molecules, quantum chemistry

• Gomes et al. Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity. Paper link.

  • Example code: PyTorch
  • Tags: binding affinity prediction, molecules, proteins

• Schütt et al. SchNet: A continuous-filter convolutional neural network for modeling quantum interactions. Paper link.

  • Example code: PyTorch
  • Tags: molecules, quantum chemistry

• Li et al. Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forcasting. Paper link.

  • Example code: Pytorch
  • Tags: Static discrete temporal graph, traffic forecasting

2016

• Li et al. Gated Graph Sequence Neural Networks. Paper link.
  • Example code: PyTorch
  • Tags: question answering
• Defferrard et al. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. Paper link.
  • Example code: PyTorch on image classification, PyTorch on node classification
  • Tags: image classification, graph classification, node classification
• Monti et al. Geometric deep learning on graphs and manifolds using mixture model CNNs. Paper link.
  • Example code: PyTorch on image classification, PyTorch on node classification, MXNet on node classification
  • Tags: image classification, graph classification, node classification
• Kearnes et al. Molecular Graph Convolutions: Moving Beyond Fingerprints. Paper link.
  • Example code: PyTorch, PyTorch for custom data
  • Tags: molecular property prediction
• Trouillon et al. Complex Embeddings for Simple Link Prediction. Paper link.
  • Example code: PyTorch, PyTorch for custom data
  • Tags: knowledge graph
• Thomas et al. Variational Graph Auto-Encoders. Paper link.
  • Example code: PyTorch
  • Tags: link prediction

2015

• Tang et al. LINE: Large-scale Information Network Embedding. Paper link.

  • Example code: PyTorch on OGB
  • Tags: network embedding, transductive learning, OGB, link prediction

• Sheng Tai et al. Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks. Paper link.

  • Example code: PyTorch, MXNet
  • Tags: sentiment classification

• Vinyals et al. Order Matters: Sequence to sequence for sets. Paper link.

  • Pooling module: PyTorch, MXNet
  • Tags: graph classification

• Lin et al. Learning Entity and Relation Embeddings for Knowledge Graph Completion. Paper link.

  • Example code: PyTorch, PyTorch for custom data
  • Tags: knowledge graph

• Yang et al. Embedding Entities and Relations for Learning and Inference in Knowledge Bases. Paper link.

  • Example code: PyTorch, PyTorch for custom data
  • Tags: knowledge graph

• Duvenaud et al. Convolutional Networks on Graphs for Learning Molecular Fingerprints. Paper link.

  • Example code: PyTorch, PyTorch for custom data
  • Tags: molecules, molecular property prediction

2014

• Perozzi et al. DeepWalk: Online Learning of Social Representations. Paper link.

  • Example code: PyTorch on OGB
  • Tags: network embedding, transductive learning, OGB, link prediction

• Fischer et al. A Hausdorff Heuristic for Efficient Computation of Graph Edit Distance. Paper link.

  • Example code: PyTorch
  • Tags: graph edit distance, graph matching

2013

• Bordes et al. Translating Embeddings for Modeling Multi-relational Data. Paper link.
  • Example code: PyTorch, PyTorch for custom data
  • Tags: knowledge graph

2011

• Fankhauser et al. Speeding Up Graph Edit Distance Computation through Fast Bipartite Matching. Paper link.

  • Example code: PyTorch
  • Tags: graph edit distance, graph matching

• Nickel et al. A Three-Way Model for Collective Learning on Multi-Relational Data. Paper link.

  • Example code: PyTorch, PyTorch for custom data
  • Tags: knowledge graph

2010

• Hoffman et al. Online Learning for Latent Dirichlet Allocation. Paper link.
  • Example code: PyTorch
  • Tags: sklearn, decomposition, latent Dirichlet allocation

2009

• Riesen et al. Speeding Up Graph Edit Distance Computation with a Bipartite Heuristic. Paper link.
  • Example code: PyTorch
  • Tags: graph edit distance, graph matching

2006

• Neuhaus et al. Fast Suboptimal Algorithms for the Computation of Graph Edit Distance. Paper link.
  • Example code: PyTorch
  • Tags: graph edit distance, graph matching

2002

• Zhu & Ghahramani. Learning from Labeled and Unlabeled Data with Label Propagation. Paper link.
  • Example code: PyTorch
  • Tags: node classification, label propagation

1998

• Page et al. The PageRank Citation Ranking: Bringing Order to the Web. Paper link.
  • Example code: PyTorch
  • Tags: PageRank