arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.03597cs.LGcs.AI
收藏

面向异质图分布外泛化的少样本因果表示学习

Few-Shot Causal Representation Learning for Out-of-Distribution Generalization on Heterogeneous Graphs

School of Computing, Macquarie University(麦考瑞大学计算学院);Hong Kong University of Science and Technology(香港科技大学)

Pengfei Ding, Yan Wang, Guanfeng Liu, Nan Wang, Xiaofang Zhou

AI总结:

针对异质图少样本学习中源图、训练与测试数据分布偏移问题,提出COHF,利用结构因果模型、变分自编码器异质图网络和元学习实现分布外泛化,并在七个数据集上验证优势。

摘要:

异质图少样本学习(HGFL)已被开发用于解决异质图(HG)中的标签稀疏问题,异质图由多种类型的节点和边组成。HGFL的核心思想是从源异质图中标签丰富的类别提取知识,将这些知识迁移到目标异质图,以促进利用少量带标签训练数据学习新类别,最终在无标签测试数据上进行预测。现有方法通常假设源异质图、训练数据和测试数据都共享相同分布。然而在实践中,由于两个原因,这三类数据之间不可避免地存在分布偏移:(1)与目标异质图分布匹配的源异质图可用性有限;(2)目标异质图的数据生成机制不可预测。这种分布偏移导致现有方法的知识迁移无效且学习性能较差,从而引出了HGFL中一个新颖的分布外(OOD)泛化问题。为解决这一具有挑战性的问题,我们提出了一种新颖的因果OOD异质图少样本学习模型,即COHF。在COHF中,我们首先使用结构因果模型刻画异质图中的分布偏移,为HGFL中的OOD泛化建立不变性原则。随后,遵循该不变性原则,我们提出一种新的基于变分自编码器的异质图神经网络,以缓解分布偏移的影响。最后,通过将该网络与新颖的元学习框架相结合,COHF有效地将知识迁移到目标异质图,以利用少量带标签数据预测新类别。在七个真实世界数据集上的大量实验表明,COHF相较于最先进方法具有优越性能。

英文摘要:

Heterogeneous graph few-shot learning (HGFL) has been developed to address the label sparsity issue in heterogeneous graphs (HGs), which consist of various types of nodes and edges. The core concept of HGFL is to extract knowledge from rich-labeled classes in a source HG, transfer this knowledge to a target HG to facilitate learning new classes with few-labeled training data, and finally make predictions on unlabeled testing data. Existing methods typically assume that the source HG, training data, and testing data all share the same distribution. However, in practice, distribution shifts among these three types of data are inevitable due to two reasons: (1) the limited availability of the source HG that matches the target HG distribution, and (2) the unpredictable data generation mechanism of the target HG. Such distribution shifts result in ineffective knowledge transfer and poor learning performance in existing methods, thereby leading to a novel problem of out-of-distribution (OOD) generalization in HGFL. To address this challenging problem, we propose a novel Causal OOD Heterogeneous graph Few-shot learning model, namely COHF. In COHF, we first characterize distribution shifts in HGs with a structural causal model, establishing an invariance principle for OOD generalization in HGFL. Then, following this invariance principle, we propose a new variational autoencoder-based heterogeneous graph neural network to mitigate the impact of distribution shifts. Finally, by integrating this network with a novel meta-learning framework, COHF effectively transfers knowledge to the target HG to predict new classes with few-labeled data. Extensive experiments on seven real-world datasets have demonstrated the superior performance of COHF over the state-of-the-art methods.

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。

↑