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

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