Cross-Domain Few-Shot Graph Classification
This work addresses the problem of few-shot learning for graph classification across domains, which is incremental as it builds on existing meta-learning frameworks with new benchmarks and an encoder.
The paper tackled few-shot graph classification across domains with different feature spaces by introducing three new cross-domain benchmarks and proposing an attention-based graph encoder. The result showed that when combined with metric-based meta-learning, this encoder achieved the best average meta-test classification accuracy across all benchmarks.
We study the problem of few-shot graph classification across domains with nonequivalent feature spaces by introducing three new cross-domain benchmarks constructed from publicly available datasets. We also propose an attention-based graph encoder that uses three congruent views of graphs, one contextual and two topological views, to learn representations of task-specific information for fast adaptation, and task-agnostic information for knowledge transfer. We run exhaustive experiments to evaluate the performance of contrastive and meta-learning strategies. We show that when coupled with metric-based meta-learning frameworks, the proposed encoder achieves the best average meta-test classification accuracy across all benchmarks. The source code and data will be released here: https://github.com/kavehhassani/metagrl