When Sparse Graph Representation Learning Falls into Domain Shift: Data Augmentation for Cross-Domain Graph Meta-Learning (Student Abstract)
DOI:
https://doi.org/10.1609/aaai.v38i21.30489Keywords:
Graph Neural Networks, Few-shot Learning, Domain GeneralizationAbstract
Cross-domain Graph Meta-learning (CGML) has shown its promise, where meta-knowledge is extracted from few-shot graph data in multiple relevant but distinct domains. However, several recent efforts assume target data available, which commonly does not established in practice. In this paper, we devise a novel Cross-domain Data Augmentation for Graph Meta-Learning (CDA-GML), which incorporates the superiorities of CGML and Data Augmentation, has addressed intractable shortcomings of label sparsity, domain shift, and the absence of target data simultaneously. Specifically, our method simulates instance-level and task-level domain shift to alleviate the cross-domain generalization issue in conventional graph meta-learning. Experiments show that our method outperforms the existing state-of-the-art methods.Downloads
Published
2024-03-24
How to Cite
Niu, S., Liang, X., Zhang, S., Song, S., Zhang, X., & Zhou, X. (2024). When Sparse Graph Representation Learning Falls into Domain Shift: Data Augmentation for Cross-Domain Graph Meta-Learning (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 38(21), 23600-23601. https://doi.org/10.1609/aaai.v38i21.30489
Issue
Section
AAAI Student Abstract and Poster Program