Clarify Confused Nodes via Separated Learning | ✓ Link | 91.64 ± 0.53 | | | | | | | NCGCN | 2023-06-04 |
Clarify Confused Nodes via Separated Learning | ✓ Link | 91.55 ± 0.38 | | | | | | | NCSAGE | 2023-06-04 |
Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification? | | 91.31 ± 0.6 | | | | | | | ACMII-Snowball-3 | 2021-09-12 |
Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification? | | 90.74 ± 0.5 | | | | | | | ACM-GCN | 2021-09-12 |
The Split Matters: Flat Minima Methods for Improving the Performance of GNNs | ✓ Link | 90.64 ± 0.46% | | | | | | | Graph-MLP + SAF | 2023-06-15 |
Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification? | | 90.56 ± 0.39 | | | | | | | ACMII-Snowball-2 | 2021-09-12 |
NodeNet: A Graph Regularised Neural Network for Node Classification | | 90.21% | | | | | | | NodeNet | 2020-06-16 |
CN-Motifs Perceptive Graph Neural Networks | | 90.07± 0.43 | | | | | | | CNMPGNN | 2021-11-15 |
Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages | ✓ Link | 89.58% | | | | | | | CoLinkDist | 2021-06-16 |
Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages | ✓ Link | 89.53% | | | | | | | CoLinkDistMLP | 2021-06-16 |
Optimization of Graph Neural Networks with Natural Gradient Descent | ✓ Link | 89.36 ± 0.57 | | | | | | | SSP | 2020-08-21 |
Inferring from References with Differences for Semi-Supervised Node Classification on Graphs | ✓ Link | 88.90 | | | | | | | 3ference | 2022-04-11 |
SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels | ✓ Link | 88.88% | | | | | | | SplineCNN | 2017-11-24 |
Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages | ✓ Link | 88.86% | | | | | | | LinkDist | 2021-06-16 |
Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages | ✓ Link | 88.79% | | | | | | | LinkDistMLP | 2021-06-16 |
Mixup for Node and Graph Classification | ✓ Link | 87.9% | | | | | | | GCN + Mixup | 2021-06-01 |
Unifying Graph Convolutional Neural Networks and Label Propagation | ✓ Link | 87.8 ± 0.6 | | | | | | | GCN-LPA | 2020-02-17 |
Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures | ✓ Link | 86.86±0.12 | | | | | | | CGT | 2023-12-28 |
Deep Graph Contrastive Representation Learning | ✓ Link | 86.7 ± 0.1 | | | | | | | GRACE | 2020-06-07 |
DiffWire: Inductive Graph Rewiring via the Lovász Bound | ✓ Link | 86.07 | | | | | | | CT-Layer (PE) | 2022-06-15 |
Certifiable Robustness and Robust Training for Graph Convolutional Networks | ✓ Link | 86% | | | | | | | GNN RH-U | 2019-06-28 |
Multi-Mask Aggregators for Graph Neural Networks | ✓ Link | 86.00% | | | | | | | MMA | 2022-11-24 |
DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters | ✓ Link | 85.2 ± 0.3 | | | | | | | DFNet-ATT | 2019-10-24 |
GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation | ✓ Link | 83.0% | | | | | | | GResNet(LoopyNet) | 2019-09-12 |
Transferring Robustness for Graph Neural Network Against Poisoning Attacks | ✓ Link | 82.92 ± 0.13 | | | | | | | PA-GNN | 2019-08-20 |
GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation | ✓ Link | 82.2% | | | | | | | GResNet(GAT) | 2019-09-12 |
Deeper-GXX: Deepening Arbitrary GNNs | | 81.92±0.13 | | | | | | | TGCL+ResNet | 2021-10-26 |
[]() | | 81.9% | fixed 20 per class | | | | | | DSGCN | |
GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation | ✓ Link | 81.7% | | | | | | | GResNet(GCN) | 2019-09-12 |
GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation | ✓ Link | 81.2% | | | | | | | LoopyNet | 2019-09-12 |
MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing | ✓ Link | 80.8% | 20 per node | | YES | | | | MixHop | 2019-04-30 |
Multi-Task Graph Autoencoders | ✓ Link | 80.40% | 20 per node | | YES | | | | MTGAE | 2018-11-07 |
Hyperbolic Graph Convolutional Neural Networks | ✓ Link | 80.3% | | | | | | | HGCN | 2019-10-28 |
Cleora: A Simple, Strong and Scalable Graph Embedding Scheme | ✓ Link | 80.2 | | | | | | | Cleora | 2021-02-03 |
Structure fusion based on graph convolutional networks for semi-supervised classification | | 80.0% | | | | | | | SPF-GCN | 2019-07-02 |
Diffusion Improves Graph Learning | ✓ Link | 79.95% | | | | | | | JK (Heat Diffusion) | 2019-10-28 |
AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models | ✓ Link | 79.76 ± 0.27 | | | | | | | AdaGCN | 2019-08-14 |
Predict then Propagate: Graph Neural Networks meet Personalized PageRank | ✓ Link | 79.73 ± 0.31 | | | YES | | | | APPNP | 2018-10-14 |
Robust Graph Data Learning via Latent Graph Convolutional Representation | | 79.7% | | | | | | | GOCN | 2019-04-26 |
Auto-GNN: Neural Architecture Search of Graph Neural Networks | | 79.7 ± 0.4% | | | | | | | AGNN-w/o share | 2019-09-07 |
GraphNAS: Graph Neural Architecture Search with Reinforcement Learning | ✓ Link | 79.6 ± 0.4% | | | | | | | GraphNAS | 2019-04-22 |
Graph U-Nets | ✓ Link | 79.6 ± 0.2% | | | | | | | Graph U-Nets | 2019-05-11 |
Large-Scale Learnable Graph Convolutional Networks | ✓ Link | 79.5% | | | | | | | LGCN sub | 2018-08-12 |
N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification | ✓ Link | 79.5% | | | | | | | N-GCN | 2018-02-24 |
Get Rid of Suspended Animation Problem: Deep Diffusive Neural Network on Graph Semi-Supervised Classification | ✓ Link | 79.5% | | | | | | | DifNet | 2020-01-22 |
Learning to Make Predictions on Graphs with Autoencoders | ✓ Link | 79.40% | | | | | | | alpha-LoNGAE | 2018-02-23 |
Fast Graph Representation Learning with PyTorch Geometric | ✓ Link | 79.4 ± 2.2 | | | | | | | APPNP | 2019-03-06 |
Graphite: Iterative Generative Modeling of Graphs | ✓ Link | 79.3 ± 0.03 | | | | | | | Graphite | 2018-03-28 |
Structure fusion based on graph convolutional networks for semi-supervised classification | | 79.3% | | | | | | | SF-GCN | 2019-07-02 |
Graph-Bert: Only Attention is Needed for Learning Graph Representations | ✓ Link | 79.3% | | | | | | | Graph-Bert | 2020-01-15 |
Graph Wavelet Neural Network | ✓ Link | 79.1% | | | | | | | GWNN | 2019-04-12 |
Understanding over-squashing and bottlenecks on graphs via curvature | ✓ Link | 79.10±0.11 | | | | | | | SDRF | 2021-11-29 |
Graph Attention Networks | ✓ Link | 79.0 ± 0.3% | fixed 20 per node | | YES | | 79.0 | | GAT | 2017-10-30 |
Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | 79.0 | | | | | | | GCN | 2016-09-09 |
A Capsule Network-based Model for Learning Node Embeddings | ✓ Link | 78.45% | | | | | | | Caps2NE | 2019-11-12 |
A Flexible Generative Framework for Graph-based Semi-supervised Learning | ✓ Link | 78.4% | 20 per node with early stopping set | | YES | | | | G3NN | 2019-05-26 |
TREE-G: Decision Trees Contesting Graph Neural Networks | ✓ Link | 78.0 | | | | | | | TREE-G | 2022-07-06 |
Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View | | 77.4 ± 0.2 | | | | | | | GCN + AdaGraph (AG) | 2019-09-07 |
Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning | ✓ Link | 77.4 ± 1.9 | | | | | | | Graph InfoClust (GIC) | 2020-09-15 |
Graph Star Net for Generalized Multi-Task Learning | ✓ Link | 77.2% | | | | | | | GraphStar | 2019-06-21 |
Revisiting Semi-Supervised Learning with Graph Embeddings | ✓ Link | 77.2% | | | | | | | Planetoid* | 2016-03-29 |
Deep Graph Infomax | ✓ Link | 76.8 ± 0.6% | | | | | | | DGI | 2018-09-27 |
Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation | ✓ Link | 75.42 ± 2.31 | | | | | | | GLNN | 2021-10-17 |
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering | ✓ Link | 74.4% | | | | | | | ChebNet | 2016-06-30 |
DiffWire: Inductive Graph Rewiring via the Lovász Bound | ✓ Link | 68.19 | | | | | | | CT-Layer | 2022-06-15 |
Deep Autoencoder-like Nonnegative Matrix Factorization for Community Detection | ✓ Link | 63.93% | | | | | | | DANMF | 2018-10-22 |
Graph Representation Learning Beyond Node and Homophily | ✓ Link | | | 88.57 | | | | | PairE | 2022-03-03 |
Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks | ✓ Link | | | 79.9 | | | | | ClusterGCN | 2019-05-20 |
Beyond Homophily: Structure-aware Path Aggregation Graph Neural Network | ✓ Link | | | | | 88.92 | | | PathNet | 2022-07-20 |
FIT-GNN: Faster Inference Time for GNNs Using Coarsening | ✓ Link | | | | | | | 0.0018 | FIT-GNN | 2024-10-19 |