Node Classification On Non Homophilic
节点分类在非同质图（异质图）上的任务旨在评估专为异质性数据集设计的模型性能。该任务关注图中跨类边多于同类边的情况，通过系统性测试和分析，揭示模型在处理异质图时的表现差异，为图神经网络的优化提供重要参考。
Chameleon (48%/32%/20% fixed splits)
Chameleon(60%/20%/20% random splits)
ACM-GCN+
Cornell (48%/32%/20% fixed splits)
Cornell (60%/20%/20% random splits)
ACMII-GCN
Deezer-Europe
ACMII-GCN+++
Film(48%/32%/20% fixed splits)
genius
ClenshawGCN
Penn94
Pubmed
Squirrel (48%/32%/20% fixed splits)
Texas (48%/32%/20% fixed splits)
Texas(60%/20%/20% random splits)
twitch-gamers
Wisconsin (48%/32%/20% fixed splits)
O(d)-NSD
Wisconsin(60%/20%/20% random splits)
ACM-GCN++