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 2602.08173math.STcs.ITcs.LGmath.ITmath.PRstat.TH
收藏

在具有上下文的多层随机块模型中社区检测的基本限制

Fundamental Limits of Community Detection in Contextual Multi-Layer Stochastic Block Models

Peking University(北京大学);Tsinghua University(清华大学)

Shuyang Gong, Dong Huang, Zhangsong Li

AI总结:

本文研究了在具有上下文的多层随机块模型中社区检测的基本限制,推导了检测和估计的阈值,并设计了高效算法以消除统计-计算间隙。

摘要:

我们考虑从高维协变量矩阵和L个稀疏网络的联合观测中进行社区检测的问题,这些网络都包含关于n个受试者潜在社区标签的噪声和不完整信息。在平均度数恒定且特征数p与n成比例增长的渐进行 regime 中,我们推导出一个明确的阈值,在此之下可以检测和估计受试者的标签。我们的结果将MN23的工作扩展到恒定度数的 regime 中,同时在网络数量为常数时解决了YLS24+中的猜想。我们通过伯努利和高斯矩之间的新比较不等式以及受启发于DHSS25的统计变体“恢复到卡方分歧减少”论证,获得了信息论下界。在算法方面,我们设计了基于计数装饰循环和装饰路径的高效算法,并证明这些算法在检测和弱恢复方面都达到尖锐阈值。特别是,我们的结果表明在这种情况下不存在统计-计算间隙。

英文摘要:

We consider the problem of community detection from the joint observation of a high-dimensional covariate matrix and $L$ sparse networks, all encoding noisy, partial information about the latent community labels of $n$ subjects. In the asymptotic regime where the networks have constant average degree and the number of features $p$ grows proportionally with $n$, we derive a sharp threshold under which detecting and estimating the subject labels is possible. Our results extend the work of \cite{MN23} to the constant-degree regime with noisy measurements, and also resolve a conjecture in \cite{YLS24+} when the number of networks is a constant. Our information-theoretic lower bound is obtained via a novel comparison inequality between Bernoulli and Gaussian moments, as well as a statistical variant of the ``recovery to chi-square divergence reduction'' argument inspired by \cite{DHSS25}. On the algorithmic side, we design efficient algorithms based on counting decorated cycles and decorated paths and prove that they achieve the sharp threshold for both detection and weak recovery. In particular, our results show that there is no statistical-computational gap in this setting.

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。

↑