Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation

Abstract

Unsupervised Graph Domain Adaptation (UGDA) has emerged as a practical solution to transfer knowledge from a label-rich source graph to a completely unlabelled target graph. However, most methods require a labelled source graph to provide supervision signals, which might not be accessible in the real-world settings due to regulations and privacy concerns. In this paper, we explore the scenario of source-free unsupervised graph domain adaptation, which tries to address the domain adaptation problem without accessing the labelled source graph. Specifically, we present a novel paradigm called GraphCTA, which performs model adaptation and graph adaptation collaboratively through a series of procedures: (1) conduct model adaptation based on node's neighborhood predictions in target graph considering both local and global information; (2) perform graph adaptation by updating graph structure and node attributes via neighborhood contrastive learning; and (3) the updated graph serves as an input to facilitate the subsequent iteration of model adaptation, thereby establishing a collaborative loop between model adaptation and graph adaptation. Comprehensive experiments are conducted on various public datasets. The experimental results demonstrate that our proposed model outperforms recent source-free baselines by large margins.

Accepted by WWW-2024

References in corpus (13)

• A Comprehensive Survey on Graph Neural Networks
• DeepWalk: Online Learning of Social Representations
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Graph Neural Networks with convolutional ARMA filters
• GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
• Network Together: Node Classification via Cross network Deep Network Embedding
• Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
• Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment
• Sparsity-Aware Sensor Collaboration for Linear Coherent Estimation
• Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization
• Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
• SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks
• CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation