Cross-Domain Few-Shot Graph Classification
DOI:
https://doi.org/10.1609/aaai.v36i6.20642Keywords:
Machine Learning (ML)Abstract
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.Downloads
Published
2022-06-28
How to Cite
Hassani, K. (2022). Cross-Domain Few-Shot Graph Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 36(6), 6856-6864. https://doi.org/10.1609/aaai.v36i6.20642
Issue
Section
AAAI Technical Track on Machine Learning I