Contrastive domain-adaptive graph selective self-training network for cross-network edge classification

Mengqiu Shao, Peng Xue, Xi Zhou, Xiao Shen

Abstract: Highlights•Class-aware contrastive domain adaptation to mitigate intra-class domain discrepancy and enlarge inter-class domain discrepancy.•Positive and negative pseudo-labeling to specify the presence and absence of a specific class in a target node.•Potential supervised information from more target nodes can be exploited to facilitate class-aware domain alignment.