Dual Prototype-Enhanced Contrastive Framework for Class-Imbalanced Graph Domain Adaptation

Graph transfer learning, especially in unsupervised domain adaptation, aims to transfer knowledge from a label-abundant source graph to an unlabeled target graph. However, most existing approaches overlook the common issue of label imbalance in the source domain, typically assuming a balanced label distribution that rarely holds in practice. Moreover, they face challenges arising from biased knowledge in the source graph and substantial domain distribution shifts. To remedy the above challenges, we propose a dual-branch prototype-enhanced contrastive framework for class-imbalanced graph domain adaptation in this paper. Specifically, we introduce a dual-branch graph encoder to capture both local and global information, generating class-specific prototypes from a distilled anchor set. Then, a prototype-enhanced contrastive learning framework is introduced. On the one hand, we encourage class alignment between the two branches based on constructed prototypes to alleviate the bias introduced by class imbalance. On the other hand, we infer the pseudo-labels for the target domain and align sample pairs across domains that share similar semantics to reduce domain discrepancies. Experimental results show that our ImGDA outperforms the state-of-the-art methods across multiple datasets and settings. The code is available at: https: //github. com/maxin88scu/ImGDA.

Authors

• Xin Ma
• Yifan Wang Tsinghua University, Tsinghua University
• Siyu Yi College of Mathematics, Sichuan University, Chengdu, China
• Wei Ju College of Computer Science, Sichuan University, Chengdu, China
• Junyu Luo State Key Laboratory for Multimedia Information Processing, School of Computer Science, PKU-Anker LLM Lab, Peking University, Beijing, China
• Yusheng Zhao State Key Laboratory for Multimedia Information Processing, School of Computer Science, PKU-Anker LLM Lab, Peking University, Beijing, China
• Xiao Luo
• Jiancheng Lv College of Computer Science, Sichuan University Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education

Keywords

No keywords are indexed for this paper.