arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.01773cs.LGcs.AI
收藏

通过分层语义环境提升图中的分布外泛化能力

Improving out-of-distribution generalization in graphs via hierarchical semantic environments

Seoul National University(首尔大学);Institute of Computer Technology Seoul National University(首尔大学计算机技术研究所);AIGENDRUG Co Ltd(AIGENDRUG有限公司)

Yinhua Piao, Sangseon Lee, Yijingxiu Lu, Sun Kim

AI总结:

本文提出一种为每个图生成分层语义环境的新方法,通过提取变体子图和引入随机注意力机制生成全局环境,并利用新学习目标保持层级间一致性与层级内多样性,有效提升了图数据的分布外泛化能力。

摘要:

由于复杂的分布偏移和缺乏环境上下文,图领域的分布外(OOD)泛化极具挑战性。近期方法试图通过生成扁平环境来增强图OOD泛化。然而,这种扁平环境在捕捉更复杂的数据分布时存在固有的局限性。以包含多种训练环境(如骨架、大小等)的DrugOOD数据集为例,扁平上下文无法充分应对其高度异质性。因此,生成更具语义丰富性的环境以增强图不变学习来处理分布偏移成为了一个新挑战。本文提出了一种为每个图生成分层语义环境的新颖方法。首先,给定一个输入图,我们显式地从输入图中提取变体子图,以生成关于局部环境的代理预测。然后,采用随机注意力机制重新提取子图,以分层方式重新生成全局环境。此外,我们引入了一个新的学习目标,指导我们的模型学习同一层级内环境的多样性,同时保持不同层级间的一致性。这种方法使我们的模型能够考虑环境之间的关系,并促进鲁棒的图不变学习。在真实图数据上的大量实验证明了我们框架的有效性。特别是在具有挑战性的DrugOOD数据集上,我们的方法在IC50和EC50预测任务上分别比最佳基线方法实现了高达1.29%和2.83%的提升。

英文摘要:

Out-of-distribution (OOD) generalization in the graph domain is challenging due to complex distribution shifts and a lack of environmental contexts. Recent methods attempt to enhance graph OOD generalization by generating flat environments. However, such flat environments come with inherent limitations to capture more complex data distributions. Considering the DrugOOD dataset, which contains diverse training environments (e.g., scaffold, size, etc.), flat contexts cannot sufficiently address its high heterogeneity. Thus, a new challenge is posed to generate more semantically enriched environments to enhance graph invariant learning for handling distribution shifts. In this paper, we propose a novel approach to generate hierarchical semantic environments for each graph. Firstly, given an input graph, we explicitly extract variant subgraphs from the input graph to generate proxy predictions on local environments. Then, stochastic attention mechanisms are employed to re-extract the subgraphs for regenerating global environments in a hierarchical manner. In addition, we introduce a new learning objective that guides our model to learn the diversity of environments within the same hierarchy while maintaining consistency across different hierarchies. This approach enables our model to consider the relationships between environments and facilitates robust graph invariant learning. Extensive experiments on real-world graph data have demonstrated the effectiveness of our framework. Particularly, in the challenging dataset DrugOOD, our method achieves up to 1.29% and 2.83% improvement over the best baselines on IC50 and EC50 prediction tasks, respectively.

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。

↑