1:1 Accuracy: 37.31 ± 1.09
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.
논문
1:1 Accuracy: 37.81 ± 1.15
1:1 Accuracy: 37.9 ± 1.3
1:1 Accuracy: 37.70 ± 1.40
1:1 Accuracy: 37.54 ± 1.56
1:1 Accuracy: 35.70 ± 1.00
1:1 Accuracy: 34.82 ± 1.35
1:1 Accuracy: 36.53 ± 0.77
1:1 Accuracy: 37.07±0.79
1:1 Accuracy: 31.59 ± 1.15
1:1 Accuracy: 36.10 ± 1.55
1:1 Accuracy: 32.22 ± 2.34
1:1 Accuracy: 37.44 ± 1.30