Cross-Domain Few-Shot Graph Classification. (arXiv:2201.08265v1 [cs.LG])

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 …

arxiv classification graph