When Sparse Graph Representation Learning Falls into Domain Shift: Feature Augmentation for Cross-Domain Graph Meta-Learning

Simin Niu; Xun Liang; Sensen Zhang; Zhiyu Li; Xuan Zhang; Wu Bo; Hanyu Wang; Shichao Song

ICASSP 2025accepted0 citations

When Sparse Graph Representation Learning Falls into Domain Shift: Feature Augmentation for Cross-Domain Graph Meta-Learning

Simin Niu, Xun Liang, Sensen Zhang, Zhiyu Li, Xuan Zhang, Wu Bo, Hanyu Wang, Shichao Song

Abstract

Graph Meta-learning methods have improved the performance of few-shot node classification by means of applying meta-learning to the data in non-Euclidean domains. However, most works focus on adopting a single domain, ignoring the fact that tasks in various domains may be distinct, which can cause overfitting problems and thus limit generalizability. To tackle this challenge, we propose a novel Graph Meta-learning framework called Feature-Enhanced Cross-domain Graph Meta-learning that consists of two crucial modules: 1) A feature information extraction module that aims to capture discriminative node importance and simulate various node feature distributions under distinct domains; 2) A heterogeneous graph encoder module that leverages the enhanced node features and topological information to generate task-specific node embeddings with simple fine-tuning. Moreover, we meta-learn the parameters involved to ensure the generalizability in the unseen domains. Results show that our method markedly outperforms the existing state-of-the-art methods.

BibTeX

@inproceedings{icassp2025_whensparsegraphr,
  title = {When Sparse Graph Representation Learning Falls into Domain Shift: Feature Augmentation for Cross-Domain Graph Meta-Learning},
  author = {Simin Niu and Xun Liang and Sensen Zhang and Zhiyu Li and Xuan Zhang and Wu Bo and Hanyu Wang and Shichao Song and Mengwei Wang and Jiawei Yang},
  booktitle = {ICASSP 2025},
  year = {2025}
}