태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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.
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
The PubMed dataset consists of 19717 scientific publications from PubMed database pertaining to diabetes classified into one of three classes. The citation network consists of 44338 links. Each publication in the dataset is described by a TF/IDF weighted word vector from a dictionary which consists of 500 unique words. Source: https://linqs.soe.ucsc.edu/data
Node classification on Penn94
node classification on genius
node classification on twitch-gamers
Node classification on Chameleon with the fixed 48%/32%/20% splits provided by Geom-GCN.
Node classification on Deezer Europe with 50%/25%/25% random splits for training/validation/test.
Node classification on Squirrel with the fixed 48%/32%/20% splits provided by Geom-GCN.
Node classification on Wisconsin with 60%/20%/20% random splits for training/validation/test.
Node classification on Chameleon with 60%/20%/20% random splits for training/validation/test.
Node classification on Cornell with the fixed 48%/32%/20% splits provided by Geom-GCN.
Node classification on Cornell with 60%/20%/20% random splits for training/validation/test.
Node classification on Texas with 60%/20%/20% random splits for training/validation/test.
Node classification on Wisconsin with the fixed 48%/32%/20% splits provided by Geom-GCN.
Node classification on Film with the fixed 48%/32%/20% splits provided by Geom-GCN.
Node classification on Texas with the fixed 48%/32%/20% splits provided by Geom-GCN.
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.