Papers with Code · CC BY-SA 4.0
Node Classification on Non-Homophilic (Heterophilic) Graphs
There exists a non-trivial set of graphs where graph-aware models underperform their corresponding graph-agnostic models, e.g. SGC and GCN underperform MLP with 1 layer and 2 layers. Although still controversial, people believe the performance degradation results from heterophily, i.e. there exist much more inter-class edges than inner-class edges. This task aims to evaluate models designed for non-homophilic (heterophilic) datasets.
데이터셋
15개Cornell (60%/20%/20% random splits)Chameleon(60%/20%/20% random splits)Texas(60%/20%/20% random splits)Wisconsin(60%/20%/20% random splits)Chameleon (48%/32%/20% fixed splits)Squirrel (48%/32%/20% fixed splits)Deezer-EuropePenn94Cornell (48%/32%/20% fixed splits)Film(48%/32%/20% fixed splits)Texas (48%/32%/20% fixed splits)Wisconsin (48%/32%/20% fixed splits)geniustwitch-gamersPubmed