AdaGCL+ : An Adaptive Subgraph Contrastive Learning Toward Tackling Topological Bias
Large-scale graph data poses a training scalability challenge, which is generally treated by employing batch sampling methods to divide the graph into smaller subgraphs and train them in batches. However, such an approach introduces a topological bias in the local batches compared with the complete...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 47(2025), 9 vom: 04. Aug., Seite 8073-8087
|
|---|
| 1. Verfasser: |
Wang, Yili
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Liu, Yaohua,
Liu, Ninghao,
Miao, Rui,
Wang, Ying,
Wang, Xin |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2025
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|