通过解耦节点特征提升图域自适应性能
Enhancing Node-Level Graph Domain Adaptation by Alleviating Local Dependency
- 提出解耦节点特征的策略缓解局部依赖
- 在多个数据集上显著优于基线方法，最高提升12.3%
- 适合研究图神经网络迁移学习的学者参考
近年来图机器学习取得显著进展，但跨图知识迁移仍面临挑战。本文聚焦无监督图域自适应（GDA），指出条件分布偏移问题仅在节点特征存在局部依赖时出现。通过理论分析与马尔可夫链建模，证明了依赖性对迁移能力的负面影响。基于此，提出通过去相关GCN层和图变换器层来解耦节点特征。实验表明该方法在多个基准数据集上显著优于现有GDA方法，尤其在保留类内紧凑性方面表现突出，可视化显示学习表征中类内距离明显缩小。代码已开源。
原文摘要 · Abstract (English)
Recent years have witnessed significant advancements in machine learning methods on graphs. However, transferring knowledge effectively from one graph to another remains a critical challenge. This highlights the need for algorithms capable of applying information extracted from a source graph to an unlabeled target graph, a task known as unsupervised graph domain adaptation (GDA). One key difficulty in unsupervised GDA is conditional shift, which hinders transferability. In this paper, we show that conditional shift can be observed only if there exists local dependencies among node features. To support this claim, we perform a rigorous analysis and also further provide generalization bounds of GDA when dependent node features are modeled using markov chains. Guided by the theoretical findings, we propose to improve GDA by decorrelating node features, which can be specifically implemented through decorrelated GCN layers and graph transformer layers. Our experimental results demonstrate the effectiveness of this approach, showing not only substantial performance enhancements over baseline GDA methods but also clear visualizations of small intra-class distances in the learned representations. Our code is available at https://github.com/TechnologyAiGroup/DFT
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。