Node Classification On Actor

Metrics

Accuracy

Results

Performance results of various models on this benchmark

		Paper Title	Repository
NCSAGE	43.89 ± 1.33	Clarify Confused Nodes via Separated Learning
NCGCN	43.16 ± 1.32	Clarify Confused Nodes via Separated Learning
2-HiGCN	41.81±0.52	Higher-order Graph Convolutional Network with Flower-Petals Laplacians on Simplicial Complexes
IIE-GNN	39.91 ± 2.41	Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach	-
LHS	38.87±1.0	Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks	-
RDGNN-I	38.69 ± 1.41	Graph Neural Reaction Diffusion Models	-
SignGT	38.65±0.32	SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning	-
CATv3-sup	38.5±1.2	CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph
Ordered GNN	37.99 ± 1.00	Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing
MbaGCN	37.97±0.91	Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space	-
GNNMoE(SAGE-like P)	37.97±1.01	Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
SADE-GCN	37.91 ± 0.97	Self-attention Dual Embedding for Graphs with Heterophily	-
NLMLP	37.9 ± 1.3	Non-Local Graph Neural Networks
O(d)-NSD	37.81 ± 1.15	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
Gen-NSD	37.80 ± 1.22	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
Diag-NSD	37.79 ± 1.01	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
GNNMoE(GAT-like P)	37.76±0.98	Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
GloGNN++	37.7 ± 1.40	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
GGCN + UniGAP	37.69 ± 1.2	UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks
GNNMoE(GCN-like P)	37.59±1.36	Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification

0 of 62 row(s) selected.

Command Palette

Node Classification On Actor

Metrics

Results