Command Palette
Search for a command to run...
Node Classification on Non-Homophilic (Heterophilic) Graphs
The task of node classification on non-homophilous graphs (heterophilous graphs) aims to evaluate the performance of models specifically designed for heterogeneous datasets. This task focuses on graphs where edges between different classes are more common than edges within the same class, and through systematic testing and analysis, it reveals differences in how models perform when dealing with heterophilous graphs, providing crucial references for optimizing graph neural networks.
Cornell (60%/20%/20% random splits)
ACMII-GCN
Texas(60%/20%/20% random splits)
Wisconsin(60%/20%/20% random splits)
ACM-GCN++
Chameleon(60%/20%/20% random splits)
ACM-GCN+
Chameleon (48%/32%/20% fixed splits)
Squirrel (48%/32%/20% fixed splits)
Deezer-Europe
ACMII-GCN+++
Penn94
Cornell (48%/32%/20% fixed splits)
Wisconsin (48%/32%/20% fixed splits)
O(d)-NSD
genius
ClenshawGCN
Texas (48%/32%/20% fixed splits)
twitch-gamers
Film(48%/32%/20% fixed splits)
Pubmed