Node Classification On Texas

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
RDGNN-S	94.59 ± 5.97	Graph Neural Reaction Diffusion Models
RDGNN-I	93.51 ± 5.93	Graph Neural Reaction Diffusion Models
MGNN + Hetero-S (8 layers)	93.09	The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs
2-HiGCN	92.45±0.73	Higher-order Graph Convolutional Network with Flower-Petals Laplacians on Simplicial Complexes
DJ-GNN	92.43±3.15	Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters
M2M-GNN	89.19 ± 4.5	Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs
ACM-GCN+	88.38 ± 3.64	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN++	88.38 ± 3.43	Revisiting Heterophily For Graph Neural Networks
ACM-GCN++	88.38 ± 3.43	Revisiting Heterophily For Graph Neural Networks
GRADE-GAT	88.3±3.5	Graph Neural Aggregation-diffusion with Metastability
ACMII-GCN+	88.11 ± 3.24	Revisiting Heterophily For Graph Neural Networks
GCNH	87.84±3.87	GCNH: A Simple Method For Representation Learning On Heterophilous Graphs
ACM-GCN	87.84 ± 4.4	Revisiting Heterophily For Graph Neural Networks
HLP Concat	87.57 ± 5.44	Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs
FSGNN	87.30 ± 5.55	Improving Graph Neural Networks with Simple Architecture Design
H2GCN-RARE (λ=1.0)	86.76±5.80	GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy
ACMII-GCN	86.76 ± 4.75	Revisiting Heterophily For Graph Neural Networks
UGT	86.67 ±8.31	Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity
GraphSAGE + UniGAP	86.52 ± 4.8	UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks
SADE-GCN	86.49±5.12	Self-attention Dual Embedding for Graphs with Heterophily

0 of 62 row(s) selected.

Command Palette

Node Classification On Texas

평가 지표

평가 결과