arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.09490cs.LGcs.AI
收藏

利用不变性原理应对异嗜图结构分布偏移

Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts

Zhejiang University(浙江大学);Meituan(美团);The Pennsylvania State University(宾夕法尼亚州立大学);HKUST(香港科技大学)

Jinluan Yang, Zhengyu Chen, Teng Xiao, Wenqiao Zhang, Yong Lin, Kun Kuang

AI总结:

针对异嗜图节点分类中训练与测试节点结构分布偏移问题,提出HEI框架,利用异嗜信息推断潜在环境以生成不变节点表示,实现不变预测,理论保证性能,实验验证优于现有基线。

摘要:

异嗜图神经网络(HGNNs)在半监督图学习任务中展现出良好的前景。值得注意的是,大多数真实世界的异嗜图由具有不同邻居模式的节点混合组成,表现出局部节点级别的同嗜和异嗜结构。然而,现有工作仅致力于同时为异嗜和同嗜图基准上的节点分类任务设计更好的HGNN主干或架构,其对HGNN在节点上的性能分析仅基于确定的数据分布,未探索训练和测试节点之间这种结构差异所带来的影响。如何在异嗜图上学习不变的节点表示以处理这种结构差异或分布偏移仍未被探索。在本文中,我们首先从数据增强的角度讨论以往基于图的不变学习方法的局限性。然后,我们提出HEI框架,该框架能够通过结合异嗜信息来推断潜在环境,无需增强即可生成不变的节点表示,并用于异嗜图结构分布偏移下的不变预测。我们从理论上证明,所提出的方法在异嗜图结构分布偏移下能够保证性能。在各种基准和主干上的大量实验也证明了我们的方法与现有最先进基线相比的有效性。代码可在https://github.com/Yangjinluan/HEI获取。

英文摘要:

Heterophilic Graph Neural Networks (HGNNs) have shown promising results for semi-supervised learning tasks on graphs. Notably, most real-world heterophilic graphs are composed of a mixture of nodes with different neighbor patterns, exhibiting local node-level homophilic and heterophilic structures. However, existing works are only devoted to designing better HGNN backbones or architectures for node classification tasks on heterophilic and homophilic graph benchmarks simultaneously, and their analyses of HGNN performance with respect to nodes are only based on the determined data distribution without exploring the effect caused by this structural difference between training and testing nodes. How to learn invariant node representations on heterophilic graphs to handle this structure difference or distribution shifts remains unexplored. In this paper, we first discuss the limitations of previous graph-based invariant learning methods from the perspective of data augmentation. Then, we propose \textbf{HEI}, a framework capable of generating invariant node representations through incorporating heterophily information to infer latent environments without augmentation, which are then used for invariant prediction, under heterophilic graph structure distribution shifts. We theoretically show that our proposed method can achieve guaranteed performance under heterophilic graph structure distribution shifts. Extensive experiments on various benchmarks and backbones can also demonstrate the effectiveness of our method compared with existing state-of-the-art baselines. The code is available at https://github.com/Yangjinluan/HEI

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑