arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.01697cs.LGcs.AIstat.ML
收藏

不变图学习结合信息瓶颈实现分布外泛化

Invariant Graph Learning Meets Information Bottleneck for Out-of-Distribution Generalization

School of Cyber Science and Technology, University of Science and Technology of China(中国科学技术大学网络空间安全学院);Tencent(腾讯);School of Artificial Intelligence and Data Science, University of Science and Technology of China(中国科学技术大学人工智能与数据科学学院)

Wenyu Mao, Jiancan Wu, Haoyang Liu, Yongduo Sui, Xiang Wang

AI总结:

针对图分布外泛化中GNN性能下降的问题,提出InfoIGL框架,结合不变图学习与信息瓶颈,通过冗余过滤和多级对比学习提升模型对未见分布的泛化能力,实验验证其有效性。

摘要:

图分布外(OOD)泛化仍是图学习中的主要挑战,因为图神经网络(GNNs)在分布偏移下常出现严重性能下降。旨在提取不同分布间不变特征的不变学习,是近年OOD泛化的潜在方法。尽管不变学习在欧几里得数据(如图像)的OOD问题中取得成功,但因图的复杂性,其在图数据中的探索受限。现有研究(如数据增强或因果干预)要么在图操作过程中破坏不变性,要么因缺乏因果部分的监督信号而存在可靠性问题。本研究提出基于信息瓶颈理论的不变图学习(InfoIGL)框架,用于提取图的不变特征并增强模型对未见分布的泛化能力。具体而言,InfoIGL引入冗余过滤器压缩与环境因素相关的任务无关信息;结合设计的多级对比学习,在下游分类任务中最大化同类图间的互信息,从而在很大程度上保留用于预测的不变特征。InfoIGL的优势在于无需依赖不变性的监督信号即可实现强泛化能力。在合成和真实世界数据集上的实验表明,该方法在图分类任务的OOD泛化中达到了最先进的性能。源代码可在https://github.com/maowenyu-11/InfoIGL获取。

英文摘要:

Graph out-of-distribution (OOD) generalization remains a major challenge in graph learning since graph neural networks (GNNs) often suffer from severe performance degradation under distribution shifts. Invariant learning, aiming to extract invariant features across varied distributions, has recently emerged as a promising approach for OOD generation. Despite the great success of invariant learning in OOD problems for Euclidean data (i.e., images), the exploration within graph data remains constrained by the complex nature of graphs. Existing studies, such as data augmentation or causal intervention, either suffer from disruptions to invariance during the graph manipulation process or face reliability issues due to a lack of supervised signals for causal parts. In this work, we propose a novel framework, called Invariant Graph Learning based on Information bottleneck theory (InfoIGL), to extract the invariant features of graphs and enhance models' generalization ability to unseen distributions. Specifically, InfoIGL introduces a redundancy filter to compress task-irrelevant information related to environmental factors. Cooperating with our designed multi-level contrastive learning, we maximize the mutual information among graphs of the same class in the downstream classification tasks, preserving invariant features for prediction to a great extent. An appealing feature of InfoIGL is its strong generalization ability without depending on supervised signal of invariance. Experiments on both synthetic and real-world datasets demonstrate that our method achieves state-of-the-art performance under OOD generalization for graph classification tasks. The source code is available at https://github.com/maowenyu-11/InfoIGL.

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。

↑