Node Classification On Ppi

평가 지표

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	F1	Paper Title
SGAS	99.46	SGAS: Sequential Greedy Architecture Search
g2-MLP	99.71	A Proposal of Multi-Layer Perceptron with Graph Gating Unit for Graph Representation Learning and its Application to Surrogate Model for FEM
JK-LSTM	97.6	Representation Learning on Graphs with Jumping Knowledge Networks
LGCN	77.2	Large-Scale Learnable Graph Convolutional Networks
GCNII*	99.56	Simple and Deep Graph Convolutional Networks
DenseMRGCN-14	99.43	DeepGCNs: Making GCNs Go as Deep as CNNs
GCN + SAF	99.38 ± 0.01%	The Split Matters: Flat Minima Methods for Improving the Performance of GNNs
ClusterGCN	92.9	Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
DSGCN	99.09 ± 0.03	Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks
PairE	-	Graph Representation Learning Beyond Node and Homophily
GraphStar	99.4	Graph Star Net for Generalized Multi-Task Learning
ResMRGCN-28	99.41	DeepGCNs: Making GCNs Go as Deep as CNNs
GraphNAS	98.6 ± 0.1	GraphNAS: Graph Neural Architecture Search with Reinforcement Learning
GRACE	66.2	Deep Graph Contrastive Representation Learning
GaAN	98.7	GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
GraphSAINT	99.50	GraphSAINT: Graph Sampling Based Inductive Learning Method
GAT	97.3	Graph Attention Networks
SIGN	96.50	SIGN: Scalable Inception Graph Neural Networks
GAT + PGN	99.34 ± 0.02%	The Split Matters: Flat Minima Methods for Improving the Performance of GNNs
Cluster-GCN	99.36	Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks

0 of 22 row(s) selected.