Node Classification On Cornell

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
RDGNN-I	92.72 ± 5.88	Graph Neural Reaction Diffusion Models
CATv3-sup	88.8±2.1	CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph
H2GCN-RARE (λ=1.0)	87.84±4.05	GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy
FSGNN (8-hop)	87.84±6.19	Improving Graph Neural Networks with Simple Architecture Design
Ordered GNN	87.03±4.73	Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing
DJ-GNN	87.03±1.62	Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters
UniG-Encoder	86.75±6.56	UniG-Encoder: A Universal Feature Encoder for Graph and Hypergraph Node Classification
ACMII-GCN++	86.49 ± 6.73	Revisiting Heterophily For Graph Neural Networks
GCNH	86.49±6.98	GCNH: A Simple Method For Representation Learning On Heterophilous Graphs
Diag-NSD	86.49 ± 7.35	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
M2M-GNN	86.48 ± 6.1	Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs
SADE-GCN	86.21±5.59	Self-attention Dual Embedding for Graphs with Heterophily
LHS	85.96±5.1	Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks
ACMII-GCN	85.95 ± 5.64	Revisiting Heterophily For Graph Neural Networks
GloGNN++	85.95±5.10	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
Conn-NSD	85.95±7.72	Sheaf Neural Networks with Connection Laplacians
ACM-GCN++	85.68 ± 5.8	Revisiting Heterophily For Graph Neural Networks
Gen-NSD	85.68 ± 6.51	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
GGCN	85.68 ± 6.63	Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
ACM-GCN+	85.68 ± 4.84	Revisiting Heterophily For Graph Neural Networks

0 of 60 row(s) selected.

Command Palette

Node Classification On Cornell

평가 지표

평가 결과