Rank and Align: Towards Effective Source-free Graph Domain Adaptation

Rank and Align: Towards Effective Source-free Graph Domain Adaptation

Junyu Luo, Zhiping Xiao, Yifan Wang, Xiao Luo, Jingyang Yuan, Wei Ju, Langechuan Liu, Ming Zhang

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Main Track. Pages 4706-4714. https://doi.org/10.24963/ijcai.2024/520

Graph neural networks (GNNs) have achieved impressive performance in graph domain adaptation. However, extensive source graphs could be unavailable in real-world scenarios due to privacy and storage concerns. To this end, we investigate an underexplored yet practical problem of source-free graph domain adaptation, which transfers knowledge from source models instead of source graphs to a target domain. To solve this problem, we introduce a novel GNN-based approach called Rank and Align (RNA), which ranks graph similarities with spectral seriation for robust semantics learning, and aligns inharmonic graphs with harmonic graphs which close to the source domain for subgraph extraction. In particular, to overcome label scarcity, we employ the spectral seriation algorithm to infer the robust pairwise rankings, which can guide semantic learning using a similarity learning objective. To depict distribution shifts, we utilize spectral clustering and the silhouette coefficient to detect harmonic graphs, which the source model can easily classify. To reduce potential domain discrepancy, we extract domain-invariant subgraphs from inharmonic graphs by an adversarial edge sampling process, which guides the invariant learning of GNNs. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our proposed RNA.
Keywords:
Machine Learning: ML: Multi-task and transfer learning
Data Mining: DM: Mining graphs