When Sparse Graph Representation Learning Falls into Domain Shift: Data Augmentation for Cross-Domain Graph Meta-Learning (Student Abstract)
Simin Niu, Xun Liang, Sensen Zhang, Shichao Song, Xuan Zhang, Xiaoping Zhou
Abstract
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.
BibTeX
@article{Niu_Liang_Zhang_Song_Zhang_Zhou_2024, title={When Sparse Graph Representation Learning Falls into Domain Shift: Data Augmentation for Cross-Domain Graph Meta-Learning (Student Abstract)}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30489}, DOI={10.1609/aaai.v38i21.30489}, abstractNote={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.}, number={21}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Niu, Simin and Liang, Xun and Zhang, Sensen and Song, Shichao and Zhang, Xuan and Zhou, Xiaoping}, year={2024}, month={Mar.}, pages={23600-23601} }