Cross-Domain Few-Shot Graph Classification with a Reinforced Task Coordinator


  • Qiannan Zhang King Abdullah University of Science and Technology
  • Shichao Pei University of Notre Dame
  • Qiang Yang King Abdullah University of Science and Technology
  • Chuxu Zhang Brandeis University
  • Nitesh V. Chawla University of Notre Dame
  • Xiangliang Zhang University of Notre Dame



DMKM: Graph Mining, Social Network Analysis & Community Mining, ML: Graph-based Machine Learning, ML: Transfer, Domain Adaptation, Multi-Task Learning


Cross-domain graph few-shot learning attempts to address the prevalent data scarcity issue in graph mining problems. However, the utilization of cross-domain data induces another intractable domain shift issue which severely degrades the generalization ability of cross-domain graph few-shot learning models. The combat with the domain shift issue is hindered due to the coarse utilization of source domains and the ignorance of accessible prompts. To address these challenges, in this paper, we design a novel Cross-domain Task Coordinator to leverage a small set of labeled target domain data as prompt tasks, then model the association and discover the relevance between meta-tasks from the source domain and the prompt tasks. Based on the discovered relevance, our model achieves adaptive task selection and enables the optimization of a graph learner using the selected fine-grained meta-tasks. Extensive experiments conducted on molecular property prediction benchmarks validate the effectiveness of our proposed method by comparing it with state-of-the-art baselines.




How to Cite

Zhang, Q., Pei, S., Yang, Q., Zhang, C., Chawla, N. V., & Zhang, X. (2023). Cross-Domain Few-Shot Graph Classification with a Reinforced Task Coordinator. Proceedings of the AAAI Conference on Artificial Intelligence, 37(4), 4893-4901.



AAAI Technical Track on Data Mining and Knowledge Management