arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.05428cs.LG
收藏

STERLING:二分图上的协同表示学习

STERLING: Synergistic Representation Learning on Bipartite Graphs

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Northwestern University(西北大学);Korea Advanced Institute of Science & Technology(韩国科学技术院);MIT-IBM Watson AI Lab, IBM Research(麻省理工学院-IBM沃森人工智能实验室,IBM研究院);Arizona State University(亚利桑那州立大学)

Baoyu Jing, Yuchen Yan, Kaize Ding, Chanyoung Park, Yada Zhu, Huan Liu, Hanghang Tong

AI总结:

本文提出协同表示学习模型STERLING,无需负节点对即可学习二分图节点嵌入,通过最大化正节点对相似性和共聚类互信息捕获局部与全局协同性,有效提升嵌入质量。

摘要:

二分图表示学习的一个基本挑战是如何提取信息丰富的节点嵌入。自监督学习(SSL)是应对这一挑战的有前景的范式。最近的二分图SSL方法大多基于对比学习,通过区分正负节点对来学习嵌入。对比学习通常需要大量负节点对,这可能导致计算负担和语义错误。在本文中,我们提出了一种新颖的协同表示学习模型(STERLING),无需负节点对即可学习节点嵌入。STERLING保留了二分图中独特的局部和全局协同性。局部协同性通过最大化跨类型和同类型正节点对的相似性来捕获,全局协同性通过最大化共聚类的互信息来捕获。理论分析表明,STERLING能够改善嵌入空间中不同节点类型之间的连通性。在各种基准数据集和任务上的广泛实证评估证明了STERLING在提取节点嵌入方面的有效性。

英文摘要:

A fundamental challenge of bipartite graph representation learning is how to extract informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to address this challenge. Most recent bipartite graph SSL methods are based on contrastive learning which learns embeddings by discriminating positive and negative node pairs. Contrastive learning usually requires a large number of negative node pairs, which could lead to computational burden and semantic errors. In this paper, we introduce a novel synergistic representation learning model (STERLING) to learn node embeddings without negative node pairs. STERLING preserves the unique local and global synergies in bipartite graphs. The local synergies are captured by maximizing the similarity of the inter-type and intra-type positive node pairs, and the global synergies are captured by maximizing the mutual information of co-clusters. Theoretical analysis demonstrates that STERLING could improve the connectivity between different node types in the embedding space. Extensive empirical evaluation on various benchmark datasets and tasks demonstrates the effectiveness of STERLING for extracting node embeddings.

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。

↑