Bridging Domain Adaptation and Graph Neural Networks: A Tensor-Based Framework for Effective Label Propagation
Lists
Only you see this
Abstract
Graph Neural Networks (GNNs) have recently become the predominant tools for studying graph data. Despite state-of-the-art performance on graph classification tasks, GNNs are overwhelmingly trained in a single domain under supervision, thus necessitating a prohibitively high demand for labels and resulting in poorly transferable representations. To address this challenge, we propose the Label-Propagation Tensor Graph Neural Network (LP-TGNN) framework to bridge the gap between graph data and traditional domain adaptation methods. It extracts graph topological information holistically with a tensor architecture and then reduces domain discrepancy through label propagation. It is readily compatible with general GNNs and domain adaptation techniques with minimal adjustment through pseudo-labeling. Experiments on various real-world benchmarks show that our LP-TGNN outperforms baselines by a notable margin. We also validate and analyze each component of the proposed framework in the ablation study.
BibTeX
@inproceedings{wen2025bridging,
author = {Tao Wen and Elynn Chen and Yuzhou Chen and Qi Lei},
title = {{Bridging Domain Adaptation and Graph Neural Networks: A Tensor-Based Framework for Effective Label Propagation}},
booktitle = {CPAL (Proceedings Track)},
year = {2025},
url = {https://openreview.net/forum?id=erHR9IqQBQ},
}