标题： 当异质性遇到异构图：潜图引导的无监督表示学习 显示英文标题

标题： When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning

摘要： 无监督异质图表示学习（UHGRL）因其在处理无标签的实际图上的重要意义而引起了越来越多的关注。然而，尽管异质性在真实世界的异质图中普遍存在，它却被很大程度上忽略了。本文中，我们定义了语义异质性，并提出了一种名为隐图引导的无监督表示学习（LatGRL）的创新框架来解决这个问题。首先，我们开发了一种结合全局结构和属性的相似性挖掘方法，从而能够构建细粒度的同态和异态隐图来指导表示学习。此外，我们提出了一个自适应双频语义融合机制来解决节点级语义异质性的问题。为了应对现实世界数据的巨大规模，我们进一步设计了一个可扩展的实现方案。在基准数据集上的大量实验验证了我们提出的框架的有效性和效率。源代码和数据集已发布在 https://github.com/zxlearningdeep/LatGRL。 显示英文摘要

摘要： Unsupervised heterogeneous graph representation learning (UHGRL) has gained increasing attention due to its significance in handling practical graphs without labels. However, heterophily has been largely ignored, despite its ubiquitous presence in real-world heterogeneous graphs. In this paper, we define semantic heterophily and propose an innovative framework called Latent Graphs Guided Unsupervised Representation Learning (LatGRL) to handle this problem. First, we develop a similarity mining method that couples global structures and attributes, enabling the construction of fine-grained homophilic and heterophilic latent graphs to guide the representation learning. Moreover, we propose an adaptive dual-frequency semantic fusion mechanism to address the problem of node-level semantic heterophily. To cope with the massive scale of real-world data, we further design a scalable implementation. Extensive experiments on benchmark datasets validate the effectiveness and efficiency of our proposed framework. The source code and datasets have been made available at https://github.com/zxlearningdeep/LatGRL.