arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2309.13092cs.LGcs.SI

用于异构信息网络的原型增强超图学习

Prototype-Enhanced Hypergraph Learning for Heterogeneous Information Networks

University of Amsterdam(阿姆斯特丹大学);University of Johannesburg(约翰内斯堡大学)

Shuai Wang, Jiayi Shen, Athanasios Efthymiou, Stevan Rudinac, Monika Kackovic, Nachoem Wijnberg, Marcel Worring

AI总结:

针对异构信息网络中依赖元路径、难以建模高阶关系的问题,提出原型增强超图学习方法,实现无元路径的节点分类并提升鲁棒性与可解释性。

摘要:

多媒体数据中关系的多样性和复杂性导致了异构信息网络(HINs)的产生。从此类网络中捕获语义需要能够充分利用 HINs 全部丰富信息的方法。现有的 HINs 建模方法采用最初为图神经网络设计的技术,以及 HINs 分解分析,例如使用人工预定义的元路径。本文提出一种新颖的原型增强超图学习方法,用于 HINs 中的节点分类。该方法使用超图而非普通图,捕获节点之间的高阶关系,并在不依赖元路径的情况下提取语义信息。该方法利用原型的力量提升超图学习过程的鲁棒性,并有可能为底层网络结构提供人类可解释的洞察。在三个真实世界 HINs 上进行的大量实验证明了该方法的有效性。

英文摘要:

The variety and complexity of relations in multimedia data lead to Heterogeneous Information Networks (HINs). Capturing the semantics from such networks requires approaches capable of utilizing the full richness of the HINs. Existing methods for modeling HINs employ techniques originally designed for graph neural networks, and HINs decomposition analysis, like using manually predefined metapaths. In this paper, we introduce a novel prototype-enhanced hypergraph learning approach for node classification in HINs. Using hypergraphs instead of graphs, our method captures higher-order relationships among nodes and extracts semantic information without relying on metapaths. Our method leverages the power of prototypes to improve the robustness of the hypergraph learning process and creates the potential to provide human-interpretable insights into the underlying network structure. Extensive experiments on three real-world HINs demonstrate the effectiveness of our method.

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。

↑