通过学习多个不变子图提升图模型在分布外场景下的泛化能力
Subgraph Aggregation for Out-of-Distribution Generalization on Graphs
- 设计多样化的子图采样与正则机制，提取多组关键子图
- 平均聚合子图表征，使性能在分布外测试中提升24%
- 适合分子性质预测等需多子图协同的现实任务
图神经网络在真实场景中的分布外（OOD）泛化问题日益受到关注。现有方法多依赖单一因果子图实现泛化，易受虚假相关性影响，且难以捕捉图数据背后的不变模式。在分子性质预测等实际应用中，往往存在多个关键子图共同决定目标属性。为此，本文提出新框架SuGAr，通过定制化子图采样器与多样性正则项，学习一组对任务具有判别性的多样化不变子图。这些子图表征经平均聚合后，增强信号丰富度并覆盖更完整的因果结构，从而提升分布外泛化性能。在合成与真实数据集上的大量实验表明，该方法显著优于现有最优方案，在图的分布外泛化上最高提升24%。据我们所知，这是首个通过学习多组不变子图实现图级分布外泛化的研究。
原文摘要 · Abstract (English)
Out-of-distribution (OOD) generalization in Graph Neural Networks (GNNs) has gained significant attention due to its critical importance in graph-based predictions in real-world scenarios. Existing methods primarily focus on extracting a single causal subgraph from the input graph to achieve generalizable predictions. However, relying on a single subgraph can lead to susceptibility to spurious correlations and is insufficient for learning invariant patterns behind graph data. Moreover, in many real-world applications, such as molecular property prediction, multiple critical subgraphs may influence the target label property. To address these challenges, we propose a novel framework, SubGraph Aggregation (SuGAr), designed to learn a diverse set of subgraphs that are crucial for OOD generalization on graphs. Specifically, SuGAr employs a tailored subgraph sampler and diversity regularizer to extract a diverse set of invariant subgraphs. These invariant subgraphs are then aggregated by averaging their representations, which enriches the subgraph signals and enhances coverage of the underlying causal structures, thereby improving OOD generalization. Extensive experiments on both synthetic and real-world datasets demonstrate that \ours outperforms state-of-the-art methods, achieving up to a 24% improvement in OOD generalization on graphs. To the best of our knowledge, this is the first work to study graph OOD generalization by learning multiple invariant subgraphs. code: https://github.com/Nanolbw/SuGAr
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。