arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.16334cs.LGcs.AI
收藏

分布偏移下的图泛化

Graphs Generalization under Distribution Shifts

Tianjin University(天津大学);Baylor University(贝勒大学)

Qin Tian, Wenjun Wang, Chen Zhao, Minglai Shao, Wang Zhang, Dong Li

AI总结:

针对图结构数据分布偏移同时发生在节点属性和拓扑上的挑战,提出GLIDER框架,通过建模潜在变化多样化跨域变体并在表示空间最小化差异,有效提升了节点级OOD泛化性能。

摘要:

传统机器学习方法严重依赖独立同分布假设,当测试分布偏离训练分布时存在局限性。为解决这一关键问题,旨在面对未知分布偏移时实现良好泛化性能的分布外(OOD)泛化取得了重大进展。然而,由于两大主要挑战,针对图结构数据的OOD方法目前尚不清晰且仍相对未被探索。首先,图上的分布偏移常同时发生在节点属性和图拓扑上。其次,在多样的分布偏移中捕获不变信息是一项艰巨挑战。为克服这些障碍,本文引入了一个新框架,即Graph Learning Invariant Domain genERation (GLIDER)。其目标是:(1) 通过对属性分布和拓扑结构的潜在已见或未见变化进行建模,来多样化跨域的变体;(2) 在以预测语义标签为目标的空间中最小化变体的差异。大量实验结果表明,在节点特征和拓扑结构同时发生分布偏移的跨域场景下,我们的模型在节点级OOD泛化上优于基线方法。

英文摘要:

Traditional machine learning methods heavily rely on the independent and identically distribution assumption, which imposes limitations when the test distribution deviates from the training distribution. To address this crucial issue, out-of-distribution (OOD) generalization, which aims to achieve satisfactory generalization performance when faced with unknown distribution shifts, has made a significant process. However, the OOD method for graph-structured data currently lacks clarity and remains relatively unexplored due to two primary challenges. Firstly, distribution shifts on graphs often occur simultaneously on node attributes and graph topology. Secondly, capturing invariant information amidst diverse distribution shifts proves to be a formidable challenge. To overcome these obstacles, in this paper, we introduce a novel framework, namely Graph Learning Invariant Domain genERation (GLIDER). The goal is to (1) diversify variations across domains by modeling the potential seen or unseen variations of attribute distribution and topological structure and (2) minimize the discrepancy of the variation in a representation space where the target is to predict semantic labels. Extensive experiment results indicate that our model outperforms baseline methods on node-level OOD generalization across domains in distribution shift on node features and topological structures simultaneously.

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。

↑