arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.13075cs.LG
收藏

统一多域图预训练:通过域特定专家编码实现同质和异质图

Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding

School of Computer Science;Technology Tianjin University Tianjin China;North China University of Science;School of Economics;Management Beijing University of Posts;Departments of Health Technology \& Informatics;Computing The Hong Kong Polytechnic University Kowloon Hong Kong;Tianjin University;Beijing University of Posts;The Hong Kong Polytechnic University

Chundong Liang, Yongqi Huang, Dongxiao He, Peiyuan Li, Yawen Li, Di Jin, Weixiong Zhang

AI总结:

提出统一多域图预训练方法GPH²,通过域特定专家编码和任务导向专家融合策略,解决同质与异质图混合场景下的跨域分布偏移问题。

摘要:

近年来,图预训练取得了显著成功,为下游任务提供了可迁移的表示。然而,大多数现有方法仅针对同质图或异质图设计,阻碍了跨不同类型图的统一建模。这种分离与现实应用相矛盾,因为混合的同质和异质图普遍存在,且上游预训练与下游部署之间的分布偏移很常见。在本文中,我们通过实验证明,同质和异质图预训练的平衡混合有利于下游任务,并提出了一种统一的跨同质和异质图的多域图预训练方法(GPH²)。为了解决缺乏同质和异质图统一编码器的问题,我们提出了一种统一的多视图图构建方法,无需显式的图类型特定设计即可同时编码两者。为了应对混合图带来的跨域分布差异增加,我们引入了域特定专家编码。每个专家在单个图上独立预训练以捕获域特定知识,从而保护预训练编码器免受跨域差异的不利影响。对于下游任务,我们进一步设计了一种任务导向的专家融合策略,根据专家的判别优势自适应地整合多个专家。在混合图上的大量实验表明,GPH²能够实现跨图类型和域的稳定迁移,显著优于现有的图预训练方法。

英文摘要:

Graph pre-training has achieved remarkable success in recent years, delivering transferable representations for downstream adaptation. However, most existing methods are designed for either homogeneous or heterogeneous graphs, thereby hindering unified graph modeling across diverse graph types. This separation contradicts real-world applications, where mixed homogeneous and heterogeneous graphs are ubiquitous, and distribution shifts between upstream pre-training and downstream deployment are common. In this paper, we empirically demonstrate that a balanced mixture of homogeneous and heterogeneous graph pre-training benefits downstream tasks and propose a unified multi-domain \textbf{G}raph \textbf{P}re-training method across \textbf{H}omogeneous and \textbf{H}eterogeneous graphs ($\mathbf{GPH^{2}}$). To address the lack of a unified encoder for homogeneous and heterogeneous graphs, we propose a Unified Multi-View Graph Construction that simultaneously encodes both without explicit graph-type-specific designs. To cope with the increased cross-domain distribution discrepancies arising from mixed graphs, we introduce domain-specific expert encoding. Each expert is independently pre-trained on a single graph to capture domain-specific knowledge, thereby shielding the pre-training encoder from the adverse effects of cross-domain discrepancies. For downstream tasks, we further design a Task-oriented Expert Fusion Strategy that adaptively integrates multiple experts based on their discriminative strengths. Extensive experiments on mixed graphs demonstrate that $\text{GPH}^{2}$ enables stable transfer across graph types and domains, significantly outperforming existing graph pre-training 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。

↑