Methods › Graphs › Graph Models
Graph Models
The archive attaches this collection's text per method and the copies differ: 4 distinct texts across 61 of the 64 methods here. All are shown, most-carried first (a tie goes to the text carrying Papers with Code's collection boilerplate, then to the longer text); no vote is taken between them.
Text 1, carried by 56 of 64 methods:
The Graph Methods include neural network architectures for learning on graphs with prior structure information, popularly called as Graph Neural Networks (GNNs).
Recently, deep learning approaches are being extended to work on graph-structured data, giving rise to a series of graph neural networks addressing different challenges. Graph neural networks are particularly useful in applications where data are generated from non-Euclidean domains and represented as graphs with complex relationships.
Some tasks where GNNs are widely used include node classification, graph classification, link prediction, and much more.
In the taxonomy presented by Wu et al. (2019), graph neural networks can be divided into four categories: recurrent graph neural networks, convolutional graph neural networks, graph autoencoders, and spatial-temporal graph neural networks.
Image source: A Comprehensive Survey on Graph NeuralNetworks
Text 2, carried by 3 of 64 methods:
graph embeddings, can be homogeneous graph or heterogeneous graph
Text 3, carried by 1 of 64 methods:
Semi-Supervised Learning methods leverage unlabelled data as well as labelled data to increase performance on machine learning tasks. Below you can find a continuously updating list of semi-supervised learning methods (this may have overlap with self-supervised methods due to evaluation protocol similarity).
Text 4, carried by 1 of 64 methods:
Interpretability Methods seek to explain the predictions made by neural networks by introducing mechanisms to enduce or enforce interpretability. For example, LIME approximates the neural network with a locally interpretable model. Below you can find a continuously updating list of interpretability methods.
Methods
All 64 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.
| GCN Graph Convolutional Network | – | 968 |
| Graph Convolutional Networks | – | 388 |
| Graph Transformer | – | 298 |
| DCNN Diffusion-Convolutional Neural Networks | – | 277 |
| GAT Graph Attention Network | – | 197 |
| GraphSAGE | – | 132 |
| MPNN Message Passing Neural Network | – | 74 |
| DGCNN Deep Graph Convolutional Neural Network | – | 49 |
| LightGCN | – | 46 |
| GIN Graph Isomorphism Network | – | 43 |
| SSE Stochastic Steady-state Embedding | – | 41 |
| ARMA ARMA GNN | – | 38 |
| MoNet Mixture model network | – | 25 |
| RGCN Relational Graph Convolution Network | – | 22 |
| GNS Graph Network-based Simulators | – | 21 |
| SchNet Schrödinger Network | – | 20 |
| TGN Temporal Graph Network | – | 16 |
| CGNN Crystal Graph Neural Network | – | 12 |
| DGI Deep Graph Infomax | – | 10 |
| GATv2 Graph Attention Network v2 | – | 9 |
| GGS-NNs Gated Graph Sequence Neural Networks | – | 9 |
| AGCN Adaptive Graph Convolutional Neural Networks | – | 8 |
| DiffPool | – | 7 |
| GCNII | – | 7 |
| ChebNet | – | 6 |
| UNS Unsupervised Abstractive Meeting Summarization | – | 6 |
| FastGCN | – | 5 |
| MeshGraphNet | – | 5 |
| PNA Principal Neighbourhood Aggregation | – | 5 |
| BiGCN Bi-Directional Graph Convolutional Network | – | 4 |
| Graph Contrastive Coding | – | 4 |
| LGCL Learnable graph convolutional layer | – | 4 |
| BiGG | – | 3 |
| CGMM Contextual Graph Markov Model | – | 3 |
| Cluster-GCN | – | 3 |
| S-GCN Spherical Graph Convolutional Network | – | 3 |
| GCNFN Graph Convolutional Networks for Fake News Detection | – | 2 |
| GNNCL Graph Neural Networks with Continual Learning | – | 2 |
| GaAN Gated Attention Networks | – | 2 |
| MinCutPool MinCut Pooling | – | 2 |
| RE-NET Recurrent Event Network | – | 2 |
| AdaGPR | – | 1 |
| AutoGL Automated Graph Learning | – | 1 |
| CT-Layer Commute Times Layer | – | 1 |
| CayleyNet | – | 1 |
| DualGCN Dual Graph Convolutional Networks | 2018 | 1 |
| GAGNN Group-Aware Neural Network | – | 1 |
| GAP-Layer Spectral Gap Rewiring Layer | – | 1 |
| GeniePath | – | 1 |
| GraphESN Graph Echo State Network | 2010 | 1 |
| HEGCN Hierarchical Entity Graph Convolutional Network | – | 1 |
| HMGNN Heterogeneous Molecular Graph Neural Network | – | 1 |
| Hi-LANDER | – | 1 |
| IPA-GNN Instruction Pointer Attention Graph Neural Network | – | 1 |
| MXMNet Multiplex Molecular Graph Neural Network | – | 1 |
| NeuroTactic | – | 1 |
| PGC-DGCNN | – | 1 |
| PinvGCN Pseudoinverse Graph Convolutional Network | – | 1 |
| Point-GNN | – | 1 |
| Spektral | – | 1 |
| StoGCN | – | 1 |
| Symbolic Deep Learning | – | 1 |
| TaxoExpan | – | 1 |
| NN4G Neural network for graphs | 2009 | 0 |