A list for GNNs and related works.
Number | GNN | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | Spectral CNN | Spectral Networks and Locally Connected Networks on Graphs | ICLR 2014 | https://openreview.net/forum?id=DQNsQf-UsoDBa | |
2 | Deep Convolutional Networks on Graph-Structured Data | https://arxiv.org/abs/1506.05163 | |||
3 | ChebNet | Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering | https://github.com/mdeff/cnn_graph | NeurIPS 2016 | https://proceedings.neurips.cc/paper/2016/hash/04df4d434d481c5bb723be1b6df1ee65-Abstract.html |
4 | GCN | Semi-Supervised Classification with Graph Convolutional Networks | https://github.com/tkipf/gcn | ICLR 2017 | https://openreview.net/forum?id=SJU4ayYgl |
5 | SGC | Simplifying Graph Convolutional Networks | https://github.com/Tiiiger/SGC | ICML 2019 | http://proceedings.mlr.press/v97/wu19e.html |
6 | gfNN | Revisiting Graph Neural Networks: All We Have is Low-Pass Filters | https://github.com/gear/gfnn | https://arxiv.org/abs/1905.09550 | |
7 | CayleyNet | CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters | IEEE Transactions on Signal Processing | https://github.com/amoliu/CayleyNet | |
8 | MotifNet | MotifNet: a motif-based Graph Convolutional Network for directed graphs | 2018 IEEE Data Science Workshop | https://ieeexplore.ieee.org/abstract/document/8439897 | |
9 | LanczosNet | LanczosNet: Multi-Scale Deep Graph Convolutional Networks | https://github.com/lrjconan/LanczosNetwork | ICLR 2019 | https://openreview.net/forum?id=BkedznAqKQ |
10 | PPNP & APPNP | Predict then Propagate: Graph Neural Networks meet Personalized PageRank | https://github.com/klicperajo/ppnp | ICLR 2019 | https://openreview.net/forum?id=H1gL-2A9Ym |
11 | GDC | Diffusion Improves Graph Learning | https://github.com/klicperajo/gdc | NeurIPS 2019 | https://proceedings.neurips.cc/paper/2019/hash/23c894276a2c5a16470e6a31f4618d73-Abstract.html |
12 | GCNII | Simple and Deep Graph Convolutional Networks | https://github.com/chennnM/GCNII | ICML 2020 | https://proceedings.mlr.press/v119/chen20v.html |
13 | ARMA | Graph Neural Networks with convolutional ARMA filters | https://github.com/danielegrattarola/spektral/blob/master/spektral/layers/convolutional/arma_conv.py#L10 | IEEE Transactions on Pattern Analysis and Machine Intelligence | https://ieeexplore.ieee.org/abstract/document/9336270 |
14 | DFNet | DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters | https://github.com/wokas36/DFNets | NeurIPS 2019 | https://proceedings.neurips.cc/paper/2019/hash/f87522788a2be2d171666752f97ddebb-Abstract.html |
15 | Snowball and Truncated Krylov | Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks | https://github.com/PwnerHarry/Stronger_GCN | NeurIPS 2019 | https://proceedings.neurips.cc/paper/2019/hash/ccdf3864e2fa9089f9eca4fc7a48ea0a-Abstract.html |
16 | GBP | Scalable Graph Neural Networks via Bidirectional Propagation | https://github.com/chennnM/GBP | NeurIPS 2020 | https://proceedings.neurips.cc/paper/2020/hash/a7789ef88d599b8df86bbee632b2994d-Abstract.html |
17 | FisherGCN | Fisher-Bures Adversary Graph Convolutional Networks | https://github.com/D61-IA/FisherGCN | ICML 2020 | http://proceedings.mlr.press/v115/sun20a.html |
18 | DGCN | Directed Graph Convolutional Network | https://arxiv.org/abs/2004.13970 | ||
19 | SIGN | SIGN: Scalable Inception Graph Neural Networks | ICML 2020 Workshop | https://arxiv.org/abs/2004.11198 | |
20 | DiGCN | Digraph Inception Convolutional Networks | https://github.com/flyingtango/DiGCN | NeurIPS 2020 | https://proceedings.neurips.cc/paper/2020/hash/cffb6e2288a630c2a787a64ccc67097c-Abstract.html |
21 | HKGCN | Generalizing Graph Convolutional Networks via Heat Kernel | https://openreview.net/forum?id=yBJihVXahXc | ||
22 | S2GC | Simple Spectral Graph Convolution | https://github.com/allenhaozhu/SSGC | ICLR 2021 | https://openreview.net/forum?id=CYO5T-YjWZV |
23 | GPR-GNN | Adaptive Universal Generalized PageRank Graph Neural Network | https://github.com/jianhao2016/GPRGNN | ICLR 2021 | https://openreview.net/forum?id=n6jl7fLxrP |
24 | GA-MLP | On Graph Neural Networks versus Graph-Augmented MLPs | https://github.com/leichen2018/GNN_vs_GAMLP | ICLR 2021 | https://openreview.net/forum?id=tiqI7w64JG2 |
25 | MagNet | MagNet: A Neural Network for Directed Graphs | https://github.com/matthew-hirn/magnet | NeurIPS 2021 | https://openreview.net/forum?id=TRDAFiwDq8A |
26 | BernNet | BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation | https://github.com/ivam-he/BernNet | NeurIPS 2021 | https://openreview.net/forum?id=WigDnV-_Gq |
27 | EdgeNet | EdgeNets: Edge Varying Graph Neural Networks | IEEE Transactions on Pattern Analysis and Machine Intelligence | https://ieeexplore.ieee.org/abstract/document/9536420 | |
28 | AdaGNN | AdaGNN: Graph Neural Networks with Adaptive Frequency Response | https://github.com/yushundong/AdaGNN | CIKM 2021 | https://dl.acm.org/doi/abs/10.1145/3459637.3482226 |
29 | ADA-UGNN | A Unified View on Graph Neural Networks as Graph Signal Denoising | https://github.com/alge24/ADA-UGNN | CIKM 2021 | https://dl.acm.org/doi/abs/10.1145/3459637.3482225 |
30 | AirGNN | Graph Neural Networks with Adaptive Residual | https://github.com/lxiaorui/AirGNN | NeurIPS 2021 | https://proceedings.neurips.cc/paper/2021/hash/50abc3e730e36b387ca8e02c26dc0a22-Abstract.html |
31 | ADC | Adaptive Diffusion in Graph Neural Networks | https://github.com/abcbdf/ADC | NeurIPS 2021 | https://proceedings.neurips.cc/paper/2021/hash/c42af2fa7356818e0389593714f59b52-Abstract.html |
32 | U-GCN | Universal Graph Convolutional Networks | https://github.com/jindi-tju/U-GCN | NeurIPS 2021 | https://papers.nips.cc/paper/2021/hash/5857d68cd9280bc98d079fa912fd6740-Abstract.html |
33 | BM-GCN | Block Modeling-Guided Graph Convolutional Neural Networks | https://github.com/hedongxiao-tju/BM-GCN | AAAI 2022 | https://ojs.aaai.org/index.php/AAAI/article/view/20319 |
34 | Ortho-GConv | Orthogonal Graph Neural Networks | https://github.com/KaiGuo20/Ortho-GConv | AAAI 2022 | https://ojs.aaai.org/index.php/AAAI/article/view/20316 |
35 | pGNN | p-Laplacian Based Graph Neural Networks | https://github.com/guoji-fu/pgnns | ICML 2022 | https://proceedings.mlr.press/v162/fu22e.html |
36 | Spec-GN and Norm-GN | A New Perspective on the Effects of Spectrum in Graph Neural Networks | https://github.com/qslim/gnn-spectrum | ICML 2022 | https://proceedings.mlr.press/v162/yang22n.html |
37 | JacobiConv | How Powerful are Spectral Graph Neural Networks | https://github.com/GraphPKU/JacobiConv | ICML 2022 | https://proceedings.mlr.press/v162/wang22am.html |
38 | G2CN | G2CN: Graph Gaussian Convolution Networks with Concentrated Graph Filters | ICML 2022 | https://proceedings.mlr.press/v162/li22h.html | |
39 | ChebNetII | Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited | NeurIPS 2022 | https://arxiv.org/abs/2202.03580 | |
40 | EvenNet | EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks | NeurIPS 2022 | https://arxiv.org/abs/2205.13892 | |
41 | SigMagNet | SigMaNet: One Laplacian to Rule Them All | https://arxiv.org/abs/2205.13459 | ||
42 | Spectral-SGCN-I, Spectral-SGCN-II, Spectral-S2GCN, and Singned-Magnet | Signed Graph Neural Networks: A Frequency Perspective | https://arxiv.org/abs/2208.07323 |
Number | GNN | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | GraphWave | Learning Structural Node Embeddings via Diffusion Wavelets | https://github.com/benedekrozemberczki/GraphWaveMachine | KDD 2018 | https://www-cs.stanford.edu/~jure/pubs/graphwave-kdd18.pdf |
2 | GWNN | Graph Wavelet Neural Network | https://github.com/benedekrozemberczki/GraphWaveletNeuralNetwork | ICLR 2019 | https://openreview.net/forum?id=H1ewdiR5tQ |
3 | HANet | Fast Haar Transforms for Graph Neural Networks | Neural Networks | https://www.sciencedirect.com/science/article/abs/pii/S0893608020301568 | |
4 | MathNet | MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning | https://arxiv.org/abs/2007.11202 | ||
5 | UFGConv and UFGPool | How Framelets Enhance Graph Neural Networks | https://github.com/YuGuangWang/UFG | ICML 2021 | http://proceedings.mlr.press/v139/zheng21c.html |
Number | GNN or method | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | Diffusion Scattering Transforms on Graphs | ICLR 2019 | https://openreview.net/forum?id=BygqBiRcFQ | ||
2 | Stability of Graph Scattering Transforms | https://github.com/alelab-upenn/graph-scattering-transforms | NeurIPS 2019 | https://proceedings.neurips.cc/paper/2019/hash/3ce3bd7d63a2c9c81983cc8e9bd02ae5-Abstract.html | |
3 | Geometric Scattering for Graph Data Analysis | ICML 2019 | http://proceedings.mlr.press/v97/gao19e.html | ||
4 | Graph convolutional neural networks via scattering | https://github.com/dmzou/SCAT | Applied and Computational Harmonic Analysis | https://www.sciencedirect.com/science/article/abs/pii/S1063520318300678 | |
5 | Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds | ICML 2020 | https://proceedings.mlr.press/v107/perlmutter20a.html | ||
5 | Data-Driven Learning of Geometric Scattering Networks | https://arxiv.org/abs/2010.02415 | |||
6 | Understanding Graph Neural Networks with Asymmetric Geometric Scattering Transforms | https://arxiv.org/abs/1911.06253 | |||
7 | Scattering GCN | Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks | https://github.com/dms-net/scatteringGCN | NeurIPS 2020 | https://proceedings.neurips.cc/paper/2020/hash/a6b964c0bb675116a15ef1325b01ff45-Abstract.html |
8 | GSAN | Geometric Scattering Attention Networks | https://github.com/dms-net/Attention-based-Scattering | ICASSP | https://ieeexplore.ieee.org/abstract/document/9414557/ |
Number | GNN | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | Bayesian GCN | Bayesian graph convolutional neural networks for semi-supervised classification | https://github.com/huawei-noah/BGCN | AAAI 2019 | https://ojs.aaai.org//index.php/AAAI/article/view/4531 |
2 | GPN | Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification | https://github.com/stadlmax/Graph-Posterior-Network | NeurIPS 2021 | https://papers.nips.cc/paper/2021/hash/95b431e51fc53692913da5263c214162-Abstract.html |
Number | Graph Pooling | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | LaPool | Towards Interpretable Sparse Graph Representation Learning with Laplacian Pooling | https://arxiv.org/abs/1905.11577 | ||
2 | EigenPooling | Graph Convolutional Networks with EigenPooling | https://github.com/alge24/eigenpooling | KDD 2019 | https://dl.acm.org/doi/10.1145/3292500.3330982 |
3 | HaarPool | Haar Graph Pooling | https://github.com/YuGuangWang/HaarPool | ICML 2020 | http://proceedings.mlr.press/v119/wang20m.html |
Number | GNN | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | AGNN | Attention-based Graph Neural Network for Semi-supervised Learning | https://github.com/dawnranger/pytorch-AGNN | https://arxiv.org/abs/1803.03735 | |
2 | GAT | Graph Attention Network | https://github.com/PetarV-/GAT | ICLR 2018 | https://openreview.net/forum?id=rJXMpikCZ |
3 | MCN | Higher-order Graph Convolutional Networks | |||
4 | CS-GNN | Measuring and Improving the Use of Graph Information in Graph Neural Networks | https://github.com/yifan-h/CS-GNN | ICLR 2020 | https://openreview.net/forum?id=rkeIIkHKvS |
5 | MixHop | MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing | https://github.com/samihaija/mixhop | ICML 2019 | http://proceedings.mlr.press/v97/abu-el-haija19a.html |
6 | GaAN | GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs | https://github.com/jennyzhang0215/GaAN | UAI 2018 | http://www.auai.org/uai2018/proceedings/papers/139.pdf |
7 | GAM | Graph Classification using Structural Attention | https://github.com/benedekrozemberczki/GAM | KDD 2018 | https://dl.acm.org/doi/abs/10.1145/3219819.3219980 |
8 | hGANet | Graph Representation Learning via Hard and Channel-Wise Attention Networks | KDD 2019 | https://dl.acm.org/doi/abs/10.1145/3292500.3330897 | |
9 | RGCN and RGAT | Relational Graph Attention Networks | https://github.com/babylonhealth/rgat | https://arxiv.org/abs/1904.05811 | |
10 | C-GAT | Improving Graph Attention Networks with Large Margin-based Constraints | NeurIPS 2019 Workshop | https://grlearning.github.io/papers/43.pdf | |
11 | FAGCN | Beyond Low-frequency Information in Graph Convolutional Networks | https://github.com/bdy9527/FAGCN | AAAI 2021 | https://ojs.aaai.org/index.php/AAAI/article/view/16514 |
12 | CAT-I and CAT-E | Learning Conjoint Attentions for Graph Neural Nets | ICLR 2021 | https://openreview.net/forum?id=SMU_hbhhEQ | |
13 | SuperGAT | How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision | https://github.com/dongkwan-kim/SuperGAT | ICLR 2021 | https://openreview.net/forum?id=Wi5KUNlqWty |
14 | GATv2 | How Attentive are Graph Attention Networks? | https://github.com/tech-srl/how_attentive_are_gats | ICLR 2022 | https://openreview.net/forum?id=F72ximsx7C1 |
Number | Graph Pooling | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | SortPooling | An End-to-End Deep Learning Architecture for Graph Classification | https://github.com/muhanzhang/DGCNN | AAAI 2018 | https://ojs.aaai.org/index.php/AAAI/article/view/11782 |
2 | DiffPool | Hierarchical Graph Representation Learning with Differentiable Pooling | https://github.com/RexYing/diffpool | NeurIPS 2018 | https://proceedings.neurips.cc/paper/2018/hash/e77dbaf6759253c7c6d0efc5690369c7-Abstract.html |
3 | gPool and gUnpool | Graph U-Nets | https://github.com/HongyangGao/Graph-U-Nets | ICML 2019 | http://proceedings.mlr.press/v97/gao19a.html |
4 | SAGPool | Self-Attention Graph Pooling | https://github.com/inyeoplee77/SAGPool | ICML 2019 | https://proceedings.mlr.press/v97/lee19c.html |
5 | Relational Pooling | Relational Pooling for Graph Representations | https://github.com/PurdueMINDS/RelationalPooling | ICML 2019 | http://proceedings.mlr.press/v97/murphy19a.html |
6 | HPL-SL | Hierarchical Graph Pooling with Structure Learning | https://github.com/cszhangzhen/HGP-SL | https://arxiv.org/abs/1911.05954 | |
7 | StructPool | StructPool: Structured Graph Pooling via Conditional Random Fields | https://github.com/Nate1874/StructPool | ICLR 2020 | https://openreview.net/forum?id=BJxg_hVtwH |
8 | MinCutPool | Spectral Clustering with Graph Neural Networks for Graph Pooling | https://github.com/FilippoMB/Spectral-Clustering-with-Graph-Neural-Networks-for-Graph-Pooling | ICML 2020 | https://proceedings.mlr.press/v119/bianchi20a.html |
9 | GSAPool | Structure-Feature based Graph Self-adaptive Pooling | WWW 2020 | https://dl.acm.org/doi/10.1145/3366423.3380083 | |
10 | NDP | Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling | https://github.com/danielegrattarola/decimation-pooling | IEEE Transactions on Neural Networks and Learning Systems | https://ieeexplore.ieee.org/abstract/document/9311759 |
11 | MxPool | MxPool: Multiplex Pooling for Hierarchical Graph Representation Learning | https://github.com/JucatL/MxPool/ | https://arxiv.org/abs/2004.06846 | |
12 | VIPool | Graph Cross Networks with Vertex Infomax Pooling | https://github.com/limaosen0/GXN | NeurIPS 2020 | https://proceedings.neurips.cc/paper/2020/hash/a26398dca6f47b49876cbaffbc9954f9-Abstract.html |
13 | GMT | Accurate Learning of Graph Representations with Graph Multiset Pooling | https://github.com/JinheonBaek/GMT | ICLR 2021 | https://openreview.net/forum?id=JHcqXGaqiGn |
14 | iPool | iPool—Information-Based Pooling in Hierarchical Graph Neural Networks | IEEE Transactions on Neural Networks and Learning Systems | https://ieeexplore.ieee.org/document/9392315 |
Number | HGNN | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | HetGNN | Heterogeneous Graph Neural Network | https://github.com/chuxuzhang/KDD2019_HetGNN | KDD 2019 | https://dl.acm.org/doi/10.1145/3292500.3330961 |
2 | HAN | Heterogeneous Graph Attention Network | https://github.com/Jhy1993/HAN | WWW 2019 | https://dl.acm.org/doi/10.1145/3292500.3330961 |
3 | MAGNN | MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding | https://github.com/cynricfu/MAGNN | WWW 2020 | https://dl.acm.org/doi/10.1145/3366423.3380297 |
Number | CGNN or method | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | GCAPS-CNN | Graph Capsule Convolutional Neural Networks | https://github.com/vermaMachineLearning/Graph-Capsule-CNN-Networks/ | https://arxiv.org/abs/1805.08090 | |
2 | CapsGNN | Capsule Graph Neural Network | https://github.com/benedekrozemberczki/CapsGNN | ICLR 2019 | https://openreview.net/forum?id=Byl8BnRcYm |
3 | NCGNN | NCGNN: Node-level Capsule Graph Neural Network | https://arxiv.org/abs/2012.03476 | ||
4 | HGCN | Hierarchical Graph Capsule Network | https://github.com/uta-smile/HGCN | AAAI 2021 | https://ojs.aaai.org/index.php/AAAI/article/view/17268 |
Number | GNODE or GNPDE or method | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | Graph Neural Ordinary Differential Equations | https://github.com/Zymrael/gde | https://arxiv.org/abs/1911.07532 | ||
2 | Ordinary differential equations on graph networks | https://openreview.net/forum?id=SJg9z6VFDr | |||
3 | CGF | Continuous Graph Flow | https://arxiv.org/abs/1908.02436 | ||
4 | CGNN | Continuous Graph Neural Networks | https://github.com/DeepGraphLearning/ContinuousGNN | ICML 2020 | https://proceedings.mlr.press/v119/xhonneux20a.html |
5 | NDCN | Neural Dynamics on Complex Networks | https://github.com/calvin-zcx/ndcn | KDD 2020 | https://dl.acm.org/doi/abs/10.1145/3394486.3403132 |
6 | DeltaGN and OGN | Hamiltonian Graph Networks with ODE Integrators | NeurIPS 2019 Workshop | https://ml4physicalsciences.github.io/2019/files/NeurIPS_ML4PS_2019_30.pdf | |
7 | CFD-GCN | Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction | https://github.com/locuslab/cfd-gcn | ICML 2020 | https://proceedings.mlr.press/v119/de-avila-belbute-peres20a.html |
8 | GKN | Neural Operator: Graph Kernel Network for Partial Differential Equations | https://github.com/zongyi-li/graph-pde | ICLR 2020 Workshop | https://openreview.net/forum?id=fg2ZFmXFO3 |
9 | MGKN | Multipole Graph Neural Operator for Parametric Partial Differential Equations | https://github.com/zongyi-li/graph-pde | NeurIPS 2020 | https://proceedings.neurips.cc/paper/2020/hash/4b21cf96d4cf612f239a6c322b10c8fe-Abstract.html |
10 | Learning continuous-time PDEs from sparse data with graph neural networks | ICLR 2021 | https://openreview.net/forum?id=aUX5Plaq7Oy | ||
11 | GRAND | GRAND: Graph Neural Diffusion | https://github.com/twitter-research/graph-neural-pde | ICML 2021 | https://proceedings.mlr.press/v139/chamberlain21a.html |
12 | NODEC | Neural Ordinary Differential Equation Control of Dynamics on Graphs | https://github.com/asikist/nnc | https://arxiv.org/abs/2006.09773 |
Number | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|
1 | Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning | https://github.com/liqimai/gcn | AAAI 2018 | https://ojs.aaai.org/index.php/AAAI/article/view/11604 |
2 | DeepGCNs: Can GCNs Go as Deep as CNNs? | https://github.com/lightaime/deep_gcns | ICCV 2019 | https://openaccess.thecvf.com/content_ICCV_2019/html/Li_DeepGCNs_Can_GCNs_Go_As_Deep_As_CNNs_ICCV_2019_paper.html |
3 | Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View | AAAI 2020 | https://ojs.aaai.org//index.php/AAAI/article/view/5747 | |
4 | Graph Neural Networks Exponentially Lose Expressive Power for Node Classification | https://github.com/delta2323/gnn-asymptotics | ICLR 2020 | https://openreview.net/forum?id=S1ldO2EFPr |
5 | A Note on Over-Smoothing for Graph Neural Networks | https://github.com/Chen-Cai-OSU/GNN-Over-Smoothing | ICML 2020 Workshop | https://arxiv.org/abs/2006.13318 |
6 | Revisiting Over-smoothing in Deep GCNs | https://arxiv.org/abs/2003.13663 | ||
7 | Measuring and Improving the Use of Graph Information in Graph Neural Networks | https://github.com/yifan-h/CS-GNN | ICLR 2020 | https://openreview.net/forum?id=rkeIIkHKvS |
8 | Simple and Deep Graph Convolutional Networks | https://github.com/chennnM/GCNII | ICML 2020 | https://proceedings.mlr.press/v119/chen20v.html |
9 | Graph Neural Networks with Adaptive Residual | https://github.com/lxiaorui/AirGNN | NeurIPS 2021 | https://proceedings.neurips.cc/paper/2021/hash/50abc3e730e36b387ca8e02c26dc0a22-Abstract.html |
10 | Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks | https://arxiv.org/abs/2102.06462 | ||
11 | Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs | https://arxiv.org/abs/2202.04579 |
Number | Norm | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | PairNorm | PairNorm: Tackling Oversmoothing in GNNs | https://github.com/LingxiaoShawn/PairNorm | ICLR 2020 | https://openreview.net/forum?id=rkecl1rtwB |
2 | NodeNorm | Understanding and Resolving Performance Degradation in Graph Convolutional Networks | https://github.com/miafei/NodeNorm | CIKM 2021 | https://dl.acm.org/doi/abs/10.1145/3459637.3482488 |
3 | DGN | Towards Deeper Graph Neural Networks with Differentiable Group Normalization | https://github.com/Kaixiong-Zhou/DGN | NeurIPS 2020 | https://proceedings.neurips.cc/paper/2020/hash/33dd6dba1d56e826aac1cbf23cdcca87-Abstract.html |
4 | GraphNorm | GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training | https://github.com/lsj2408/GraphNorm | ICML 2021 | http://proceedings.mlr.press/v139/cai21e.html |
Number | Method or GNN | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | DropEdge | DropEdge: Towards Deep Graph Convolutional Networks on Node Classification | https://github.com/DropEdge/DropEdge | ICLR 2020 | https://openreview.net/forum?id=Hkx1qkrKPr |
1 | DropEdge | Tackling Over-Smoothing for General Graph Convolutional Networks | https://github.com/DropEdge/DropEdge | IEEE Transactions on Pattern Analysis and Machine Intelligence | https://arxiv.org/abs/2008.09864 |
2 | FastGCN | FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling | https://github.com/matenure/FastGCN | ICLR 2018 | https://openreview.net/forum?id=rytstxWAW |
3 | VR-GCN | Stochastic Training of Graph Convolutional Networks with Variance Reduction | https://github.com/thu-ml/stochastic_gcn | ICML 2018 | https://proceedings.mlr.press/v80/chen18p.html |
4 | Adaptive Sampling Towards Fast Graph Representation Learning | https://github.com/huangwb/AS-GCN | NeurIPS 2018 | https://proceedings.neurips.cc/paper/2018/hash/01eee509ee2f68dc6014898c309e86bf-Abstract.html | |
5 | Advancing GraphSAGE with A Data-driven Node Sampling | https://github.com/oj9040/GraphSAGE_RL | ICLR 2019 workshop | https://arxiv.org/abs/1904.12935 | |
6 | LADIES | Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks | https://github.com/acbull/LADIES | NeurIPS 2019 | https://proceedings.neurips.cc/paper/2019/hash/91ba4a4478a66bee9812b0804b6f9d1b-Abstract.html |
7 | BBGDC | Bayesian Graph Neural Networks with Adaptive Connection Sampling | https://github.com/armanihm/GDC | ICML 2020 | https://proceedings.mlr.press/v119/hasanzadeh20a.html |
8 | GraphSAINT | GraphSAINT: Graph Sampling Based Inductive Learning Method | https://github.com/GraphSAINT/GraphSAINT | ICLR 2020 | https://openreview.net/forum?id=BJe8pkHFwS |
9 | MVS-GNN | Minimal Variance Sampling with Provable Guarantees for Fast Training of Graph Neural Networks | KDD 2020 | https://dl.acm.org/doi/10.1145/3394486.3403192 |
Number | Method or GNN | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | On the Bottleneck of Graph Neural Networks and its Practical Implications | https://github.com/tech-srl/bottleneck/ | ICLR 2021 | https://openreview.net/forum?id=i80OPhOCVH2 | |
2 | Understanding over-squashing and bottlenecks on graphs via curvature | ICLR 2022 | https://openreview.net/forum?id=7UmjRGzp-A |
Number | Graph Transformer | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | Graph-Bert | Graph-Bert: Only Attention is Needed for Learning Graph Representations | https://github.com/jwzhanggy/Graph-Bert | https://arxiv.org/abs/2001.05140 | |
2 | GTN | Graph Transformer Networks | https://github.com/seongjunyun/Graph_Transformer_Networks | NeurIPS 2019 | https://proceedings.neurips.cc/paper/2019/hash/9d63484abb477c97640154d40595a3bb-Abstract.html |
3 | HGT | Heterogeneous Graph Transformer | https://github.com/acbull/pyHGT | WWW 2020 | https://dl.acm.org/doi/10.1145/3366423.3380027 |
4 | GT | A Generalization of Transformer Networks to Graphs | https://github.com/graphdeeplearning/graphtransformer | AAAI 2021 Workshop | https://arxiv.org/abs/2012.09699 |
5 | SAN | Rethinking Graph Transformers with Spectral Attention | https://github.com/DevinKreuzer/SAN | NeurIPS 2021 | https://openreview.net/forum?id=huAdB-Tj4yG |
6 | Graphormer | Do Transformers Really Perform Badly for Graph Representation? | https://github.com/Microsoft/Graphormer | NeurIPS 2021 | https://openreview.net/forum?id=OeWooOxFwDa |
7 | Graphormer | Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets | https://github.com/Microsoft/Graphormer | https://arxiv.org/abs/2203.04810 | |
8 | Gophormer | Gophormer: Ego-Graph Transformer for Node Classification | https://arxiv.org/abs/2110.13094 | ||
9 | SEA | SEA: Graph Shell Attention in Graph Neural Networks | https://arxiv.org/pdf/2110.10674.pdf | ||
10 | GraphiT | GraphiT: Encoding Graph Structure in Transformers | https://github.com/inria-thoth/GraphiT | https://arxiv.org/abs/2106.05667 | |
11 | Coarformer | Coarformer: Transformer for large graph via graph coarsening | https://openreview.net/forum?id=fkjO_FKVzw | ||
12 | GKAT | From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers | https://github.com/hl-hanlin/gkat | https://arxiv.org/abs/2107.07999 | |
13 | FeTA | Investigating Expressiveness of Transformer in Spectral Domain for Graphs | https://arxiv.org/abs/2201.09332 | ||
14 | GRPE | GRPE: Relative Positional Encoding for Graph Transformer | https://github.com/lenscloth/grpe | https://arxiv.org/abs/2201.12787 |
Number | Graph MLP | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | Graph-MLP | Graph-MLP: Node Classification without Message Passing in Graph | https://github.com/yanghu819/Graph-MLP | https://arxiv.org/abs/2106.04051 | |
2 | N2N | Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization | https://github.com/dongwei156/n2n | https://arxiv.org/abs/2203.12265 |
Number | GAE | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | DNGR | Deep Neural Networks for Learning Graph Representations | AAAI 2016 | https://ojs.aaai.org/index.php/AAAI/article/view/10179 | |
2 | SDNE | Structural Deep Network Embedding | |||
3 | DVNE | Deep Variational Network Embedding in Wasserstein Space | KDD 2016 | https://www.kdd.org/kdd2016/subtopic/view/structural-deep-network-embedding | |
4 | VGAE | Variational Graph Auto-Encoders | https://github.com/tkipf/gae | ||
5 | GC-MC | Graph Convolutional Matrix Completion | https://github.com/riannevdberg/gc-mc | https://arxiv.org/abs/1706.02263 | |
6 | ARVGA | Adversarially regularized graph autoencoder for graph embedding | IJCAI 2018 | https://dl.acm.org/doi/10.5555/3304889.3305023 | |
7 | NetRA | Learning deep network representations with adversarially regularized autoencoders | KDD 2018 | https://dl.acm.org/doi/10.1145/3219819.3220000 | |
8 | DeepGMG | Learning deep generative models of graphs | https://arxiv.org/abs/1803.03324 | ||
9 | GraphRNN | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models | https://github.com/JiaxuanYou/graph-generation | ICML 2018 | https://proceedings.mlr.press/v80/you18a.html |
10 | GraphVAE | Graphvae: Towards generation of small graphs using variational autoencoders | ICANN 2018 | https://link.springer.com/chapter/10.1007/978-3-030-01418-6_41 | |
11 | Constrained generation of semantically valid graphs via regularizing variational autoencoders | NeurISP 2018 | https://proceedings.neurips.cc/paper/2018/hash/1458e7509aa5f47ecfb92536e7dd1dc7-Abstract.html | ||
12 | Gravity Graph VAE and Gravity Graph AE | Gravity-Inspired Graph Autoencoders for Directed Link Prediction | https://github.com/deezer/gravity_graph_autoencoders | CIKM 2019 | https://dl.acm.org/doi/abs/10.1145/3357384.3358023 |
Number | GGAN | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | GraphGAN | GraphGAN: Graph Representation Learning with Generative Adversarial Nets | https://github.com/hwwang55/GraphGAN | AAAI 2018 | https://ojs.aaai.org/index.php/AAAI/article/view/11872 |
2 | MolGAN | MolGAN: An implicit generative model for small molecular graphs | https://arxiv.org/abs/1805.11973 | ||
3 | NetGAN | NetGAN: Generating graphs via random walks | ICML 2018 | http://proceedings.mlr.press/v80/bojchevski18a.html |
Number | Pre-training mathod | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | Strategies for Pre-training Graph Neural Networks | https://github.com/snap-stanford/pretrain-gnns/ | ICLR 2020 | https://openreview.net/forum?id=HJlWWJSFDH | |
2 | GCC | GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training | https://github.com/THUDM/GCC | KDD 2020 | https://dl.acm.org/doi/10.1145/3394486.3403168 |
Number | method | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | Adversarial Attacks on Neural Networks for Graph Data | https://github.com/danielzuegner/nettack | KDD 2018 | https://dl.acm.org/doi/10.1145/3219819.3220078 | |
2 | Certifiable Robustness and Robust Training for Graph Convolutional Networks | https://github.com/danielzuegner/robust-gcn | KDD 2020 | https://dl.acm.org/doi/abs/10.1145/3394486.3403217 | |
3 | Adversarial Attacks on Graph Neural Networks via Meta Learning | ICLR 2019 | https://openreview.net/forum?id=Bylnx209YX | ||
4 | Adversarial Attacks on Node Embeddings via Graph Poisoning | https://github.com/abojchevski/node_embedding_attack | ICML 2019 | https://proceedings.mlr.press/v97/bojchevski19a.html | |
5 | GNNGuard | GNNGuard: Defending Graph Neural Networks against Adversarial Attacks | https://github.com/mims-harvard/GNNGuard | NeurIPS 2020 | https://proceedings.neurips.cc/paper/2020/hash/690d83983a63aa1818423fd6edd3bfdb-Abstract.html |
6 | Detection and Defense of Topological Adversarial Attacks on Graphs | ICML 2021 | https://proceedings.mlr.press/v130/zhang21i.html | ||
7 | GCN-LFR | Not All Low-Pass Filters are Robust in Graph Convolutional Networks | NeurIPS 2021 | https://openreview.net/forum?id=bDdfxLQITtu |
Number | GNN or method | Paper | Code | Journal or Conference | URL |
---|---|---|---|---|---|
1 | Contrastive Multi-View Representation Learning on Graphs | https://github.com/kavehhassani/mvgrl | ICML 2020 | https://proceedings.mlr.press/v119/hassani20a.html | |
2 | Benchmarking GNNs | Benchmarking Graph Neural Networks | https://github.com/graphdeeplearning/benchmarking-gnns | https://arxiv.org/abs/2003.00982 | |
3 | FLAG | Robust Optimization as Data Augmentation for Large-scale Graphs | https://github.com/devnkong/FLAG | https://arxiv.org/abs/2010.09891 | |
4 | Interpreting and Unifying Graph Neural Networks with An Optimization Framework | WWW 2021 | https://dl.acm.org/doi/10.1145/3442381.3449953 | ||
5 | What graph neural networks cannot learn: depth vs width | ICLR 2020 | https://openreview.net/forum?id=B1l2bp4YwS | ||
6 | Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework | https://github.com/BUPT-GAMMA/CPF | WWW 2021 | https://dl.acm.org/doi/abs/10.1145/3442381.3450068 | |
7 | SUGAR | SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism | https://github.com/RingBDStack/SUGAR | WWW 2021 | https://dl.acm.org/doi/10.1145/3442381.3449822 |
8 | Towards Sparse Hierarchical Graph Classifiers | NeurIPS 2018 Workshop | https://arxiv.org/abs/1811.01287 | ||
9 | OGB | Open Graph Benchmark: Datasets for Machine Learning on Graphs | https://github.com/snap-stanford/ogb | NeurIPS 2020 | https://proceedings.neurips.cc/paper/2020/hash/fb60d411a5c5b72b2e7d3527cfc84fd0-Abstract.html |
10 | AdaGCN | AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models | https://github.com/datake/AdaGCN | ICLR 2021 | https://openreview.net/forum?id=QkRbdiiEjM |
11 | BGNN | Bilinear Graph Neural Network with Neighbor Interactions | https://github.com/zhuhm1996/bgnn | IJCAI 2020 | https://www.ijcai.org/proceedings/2020/202 |
12 | RevGNN-Deep and RevGNN-Wide | Training Graph Neural Networks with 1000 Layers | https://github.com/lightaime/deep_gcns_torch/tree/master/examples/ogb_eff/ogbn_proteins | ICML 2021 | https://proceedings.mlr.press/v139/li21o.html |
13 | OGB-LSC | OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs | https://arxiv.org/abs/2103.09430 | ||
14 | DrGCNs | Dimensional Reweighting Graph Convolutional Networks | https://arxiv.org/abs/1907.02237 | ||
15 | GAS | GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings | https://github.com/rusty1s/pyg_autoscale | ICML 2021 | http://proceedings.mlr.press/v139/fey21a.html |
16 | TWIRLS | Graph Neural Networks Inspired by Classical Iterative Algorithms | https://github.com/FFTYYY/TWIRLS | ICML 2021 | http://proceedings.mlr.press/v139/yang21g.html |
17 | GAT-Lip | Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks | ICML 2021 | http://proceedings.mlr.press/v139/dasoulas21a.html | |
18 | Analyzing the Expressive Power of Graph Neural Networks in a Spectral Perspective | https://github.com/balcilar/gnn-spectral-expressive-power | ICLR 2021 | https://openreview.net/forum?id=-qh0M9XWxnv | |
19 | Deep Graph Neural Networks with Shallow Subgraph Samplers | https://github.com/facebookresearch/shaDow_GNN | https://arxiv.org/abs/2012.01380 | ||
20 | Large-scale graph representation learning with very deep GNNs and self-supervision | https://github.com/deepmind/deepmind-research/tree/master/ogb_lsc | https://arxiv.org/abs/2107.09422 | ||
21 | GCN-LPA | Unifying Graph Convolutional Neural Networks and Label Propagation | https://github.com/hwwang55/GCN-LPA | Unifying Graph Convolutional Neural Networks and Label Propagation | |
22 | L-GCN and L2-GCN | L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks | https://github.com/VITA-Group/L2-GCN | CVPR 2020 | https://openaccess.thecvf.com/content_CVPR_2020/html/You_L2-GCN_Layer-Wise_and_Learned_Efficient_Training_of_Graph_Convolutional_Networks_CVPR_2020_paper.html |
23 | A Fair Comparison of Graph Neural Networks for Graph Classification | https://github.com/diningphil/gnn-comparison | ICLR 2020 | https://openreview.net/forum?id=HygDF6NFPB | |
24 | CurvGN | Curvature Graph Network | ICLR 2020 | https://openreview.net/forum?id=BylEqnVFDB | |
25 | GIB | Graph Information Bottleneck | https://github.com/snap-stanford/GIB | NeurIPS 2020 | https://proceedings.neurips.cc/paper/2020/hash/ebc2aa04e75e3caabda543a1317160c0-Abstract.html |
26 | ResRGAT | Improving Breadth-Wise Backpropagation in Graph Neural Networks Helps Learning Long-Range Dependencies | https://github.com/lukovnikov/resrgat | ICML 2021 | https://proceedings.mlr.press/v139/lukovnikov21a.html |
27 | Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth | ICML 2021 | https://proceedings.mlr.press/v139/xu21k.html | ||
28 | MinGE | Graph Entropy Guided Node Embedding Dimension Selection for Graph Neural Networks | https://github.com/RingBDStack/MinGE | IJCAI 2021 | https://www.ijcai.org/proceedings/2021/381 |
29 | A Flexible Generative Framework for Graph-based Semi-supervised Learning | https://github.com/jiaqima/G3NN | NeurIPS 2019 | https://proceedings.neurips.cc/paper/2019/hash/e0ab531ec312161511493b002f9be2ee-Abstract.html | |
30 | GRAND | Graph Random Neural Networks for Semi-Supervised Learning on Graphs | https://github.com/THUDM/GRAND | NeurIPS 2020 | https://proceedings.neurips.cc/paper/2020/hash/fb4c835feb0a65cc39739320d7a51c02-Abstract.html |
31 | Approximation Ratios of Graph Neural Networks for Combinatorial Problems | NeurIPS 2019 | https://proceedings.neurips.cc/paper/2019/hash/635440afdfc39fe37995fed127d7df4f-Abstract.html | ||
32 | Can Graph Neural Networks Count Substructures? | https://github.com/leichen2018/GNN-Substructure-Counting | NeurIPS 2020 | https://proceedings.neurips.cc/paper/2020/hash/75877cb75154206c4e65e76b88a12712-Abstract.html | |
33 | GNN-FiLM | GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation | https://github.com/microsoft/tf-gnn-samples | ICML 2020 | https://proceedings.mlr.press/v119/brockschmidt20a.html |
34 | Graph Attention Retrospective | https://arxiv.org/abs/2202.13060 | |||
35 | GraphWorld: Fake Graphs Bring Real Insights for GNNs | https://arxiv.org/abs/2203.00112 | |||
36 | GRAND+ | GRAND+: Scalable Graph Random Neural Networks | https://github.com/THUDM/GRAND-plus | https://arxiv.org/abs/2203.06389 | |
37 | SAGN | Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training | https://github.com/skepsun/SAGN_with_SLE | https://arxiv.org/abs/2104.09376 | |
38 | GAMLP | Graph Attention Multi-Layer Perceptron | https://github.com/pku-dair/gamlp | ||
39 | Expressiveness and Approximation Properties of Graph Neural Networks | ICLR 2022 | https://openreview.net/forum?id=wIzUeM3TAU |
Number | Paper | Journal or Conference | URL |
---|---|---|---|
1 | Graph Neural Networks: A Review of Methods and Applications | AI Open | https://www.sciencedirect.com/science/article/pii/S2666651021000012 |
2 | A Comprehensive Survey on Graph Neural Networks | IEEE Transactions on Neural Networks and Learning Systems | https://ieeexplore.ieee.org/abstract/document/9046288 |
3 | Deep Learning on Graphs: A Survey | IEEE Transactions on Knowledge and Data Engineering | https://ieeexplore.ieee.org/abstract/document/9039675 |
4 | Explainability in Graph Neural Networks: A Taxonomic Survey | https://arxiv.org/abs/2012.15445 | |
5 | Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks | https://arxiv.org/abs/2107.10234 |