1:1 Accuracy: 67.4 ± 2.21
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.
개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.
벤치마크
Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.
Dataset기록된 모델 예시MetricPaperCode
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)
논문
1:1 Accuracy: 73.56 ± 1.62
1:1 Accuracy: 62.56 ± 1.31
1:1 Accuracy: 75.31±1.92
1:1 Accuracy: 57.88 ± 1.76
F1-Score: 59.89 ± 4.12NMI: 55.80 ± 0.87
1:1 Accuracy: 61.81 ± 1.80
1:1 Accuracy: 59.0 ± 1.2
1:1 Accuracy: 76.0±2.0
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.