arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.04860cs.LGcs.DSstat.ML
收藏

多视图随机块模型

Multi-View Stochastic Block Models

Google Research(谷歌研究院);Bocconi(博科尼大学)

Vincent Cohen-Addad, Tommaso d'Orsi, Silvio Lattanzi, Rajai Nasser

AI总结:

本文提出多视图随机块模型,并设计了一种通过分别分析各图结构而可证明优于朴素并集方法的高效算法,同时给出信息论下界并通过实验验证。

摘要:

图聚类是无监督学习中的一个核心主题,具有大量实际应用。近年来,多视图图聚类因其适用于可访问多个数据源的真实场景而受到广泛关注。本文形式化了一类新的模型,称为多视图随机块模型,以刻画这一设定。针对该模型,我们首先研究直接在多个图的并集上工作的朴素高效算法。然后,我们提出一种新的高效算法,通过分别分析每个图的结构,可证明地优于先前方法。此外,我们以一个信息论下界补充我们的结果,研究该模型中可达到的极限。最后,我们通过实验评估验证了我们的结果。

英文摘要:

Graph clustering is a central topic in unsupervised learning with a multitude of practical applications. In recent years, multi-view graph clustering has gained a lot of attention for its applicability to real-world instances where one has access to multiple data sources. In this paper we formalize a new family of models, called \textit{multi-view stochastic block models} that captures this setting. For this model, we first study efficient algorithms that naively work on the union of multiple graphs. Then, we introduce a new efficient algorithm that provably outperforms previous approaches by analyzing the structure of each graph separately. Furthermore, we complement our results with an information-theoretic lower bound studying the limits of what can be done in this model. Finally, we corroborate our results with experimental evaluations.

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。

↑