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...

Description complète

Détails bibliographiques

Publié dans:	IEEE transactions on pattern analysis and machine intelligence. - 1979. - 47(2025), 9 vom: 04. Aug., Seite 8073-8087
Auteur principal:	Wang, Yili (Auteur)
Autres auteurs:	Liu, Yaohua, Liu, Ninghao, Miao, Rui, Wang, Ying, Wang, Xin
Format:	Article en ligne
Langue:	English
Publié:	2025
Accès à la collection:	IEEE transactions on pattern analysis and machine intelligence
Sujets:	Journal Article