HyperAI超神経

Node Classification On Ppi

評価指標

F1

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
F1
Paper TitleRepository
SGAS99.46SGAS: Sequential Greedy Architecture Search
g2-MLP99.71A Proposal of Multi-Layer Perceptron with Graph Gating Unit for Graph Representation Learning and its Application to Surrogate Model for FEM
JK-LSTM97.6Representation Learning on Graphs with Jumping Knowledge Networks
LGCN77.2Large-Scale Learnable Graph Convolutional Networks
GCNII*99.56Simple and Deep Graph Convolutional Networks
DenseMRGCN-1499.43DeepGCNs: Making GCNs Go as Deep as CNNs
GCN + SAF99.38 ± 0.01%The Split Matters: Flat Minima Methods for Improving the Performance of GNNs
ClusterGCN92.9Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
DSGCN99.09 ± 0.03Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks
PairE-Graph Representation Learning Beyond Node and Homophily
GraphStar99.4Graph Star Net for Generalized Multi-Task Learning
ResMRGCN-2899.41DeepGCNs: Making GCNs Go as Deep as CNNs
GraphNAS98.6 ± 0.1GraphNAS: Graph Neural Architecture Search with Reinforcement Learning
GRACE66.2Deep Graph Contrastive Representation Learning
GaAN98.7GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
GraphSAINT99.50GraphSAINT: Graph Sampling Based Inductive Learning Method
GAT97.3Graph Attention Networks
SIGN96.50SIGN: Scalable Inception Graph Neural Networks
GAT + PGN99.34 ± 0.02%The Split Matters: Flat Minima Methods for Improving the Performance of GNNs
Cluster-GCN99.36Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
0 of 22 row(s) selected.