Conference
Open access
Sep 2026
Multi-Semantic Aware Self-Supervised Learning for Multi-Label Node Classification
A multi-pseudo-label decomposition mechanism is proposed, enabling adaptive learning of multiple semantics within nodes without annotations, in a bold attempt to extend graph self-supervised learning to multi-label graphs.
Jia-Yu Zhang, Ji-Tao Zhao, Dong-Xiao He et al.
· Proceedings of the Thirty-Fi... · 0 citations