通过修复目标图边结构，显著提升GNN在跨域场景下的分类性能。
Empowering GNNs for Domain Adaptation via Denoising Target Graph
- 在目标图上添加去噪边的辅助任务，增强GNN泛化能力。
- 在时间与区域跨域数据上，性能优于现有基线方法。
- 理论证明该方法能收紧图泛化界，适用于实际跨域图学习场景。
我们研究图领域自适应中的节点分类任务，利用源图结构和标签来提升图神经网络（GNN）在目标图上的泛化能力。当图数据在不同时间或地区采集时，常出现结构域偏移，导致GNN在目标图上表现不佳。令人惊讶的是，仅在目标图上引入边去噪的辅助损失函数，即可显著提升GNN性能。基于此，我们提出GraphDeT框架，将该辅助边任务融入GNN训练流程。理论分析表明，该辅助任务可关联到以 -距离 衡量的图泛化界，通过施加约束收紧边界，从而改善泛化。实验结果表明，该方法在处理时间与区域域偏移的图数据上均优于现有基线。
原文摘要 · Abstract (English)
We explore the node classification task in the context of graph domain adaptation, which uses both source and target graph structures along with source labels to enhance the generalization capabilities of Graph Neural Networks (GNNs) on target graphs. Structure domain shifts frequently occur, especially when graph data are collected at different times or from varying areas, resulting in poor performance of GNNs on target graphs. Surprisingly, we find that simply incorporating an auxiliary loss function for denoising graph edges on target graphs can be extremely effective in enhancing GNN performance on target graphs. Based on this insight, we propose our framework, GraphDeT, a framework that integrates this auxiliary edge task into GNN training for node classification under domain adaptation. Our theoretical analysis connects this auxiliary edge task to the graph generalization bound with -distance, demonstrating such auxiliary task can imposes a constraint which tightens the bound and thereby improves generalization. The experimental results demonstrate superior performance compared to the existing baselines in handling both time and regional domain graph shifts.
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。