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 2306.08489stat.MLcs.LGmath.SP
收藏

大规模随机Kronecker图的分析与近似推断

Analysis and Approximate Inference of Large Random Kronecker Graphs

School of Electronic Information and Communications, Huazhong University of Science and Technology(华中科技大学电子信息与通信学院);Peng Cheng Laboratory(鹏城实验室);Pazhou Laboratory (Huangpu)(琶洲实验室(黄埔))

Zhenyu Liao, Yuanqian Xia, Chengmei Niu, Yong Xiao

AI总结:

本文针对大规模随机Kronecker图,利用随机矩阵理论将其邻接矩阵分解为小秩信号与噪声,提出“去噪然后求解”的推断方法,在保持性能的同时将计算复杂度降至线性。

摘要:

随机图模型在从社交网络、电信系统到生理和生物网络等各个领域发挥着越来越重要的作用。在这一背景下,随机Kronecker图模型作为审视复杂现实网络的一个突出框架而出现。在本文中,我们研究大规模随机Kronecker图,即图顶点数$N$很大。基于随机矩阵理论(RMT)和高维统计的最新进展,我们证明了一个大规模随机Kronecker图的邻接矩阵在谱范数意义上可以分解为两部分:一个秩为$O(\log N)$的小秩信号矩阵,该矩阵与图参数线性相关,以及一个零均值随机噪声矩阵。基于这一结果,我们提出了一种“去噪然后求解”的方法来推断关键图参数,显著降低了计算复杂度。我们展示了在图推断和分类上的实验来评估我们提出的方法。在这两项任务中,所提出的方法在时间成本随图大小$N$线性增长的情况下,与广泛使用的图推断(如KronFit)和图神经网络基线相比,取得了相当或更优的性能。

英文摘要:

Random graph models are playing an increasingly important role in various fields ranging from social networks, telecommunication systems, to physiologic and biological networks. Within this landscape, the random Kronecker graph model, emerges as a prominent framework for scrutinizing intricate real-world networks. In this paper, we investigate large random Kronecker graphs, i.e., the number of graph vertices $N$ is large. Built upon recent advances in random matrix theory (RMT) and high-dimensional statistics, we prove that the adjacency of a large random Kronecker graph can be decomposed, in a spectral norm sense, into two parts: a small-rank (of rank $O(\log N)$) signal matrix that is linear in the graph parameters and a zero-mean random noise matrix. Based on this result, we propose a ``denoise-and-solve'' approach to infer the key graph parameters, with significantly reduced computational complexity. Experiments on both graph inference and classification are presented to evaluate the our proposed method. In both tasks, the proposed approach yields comparable or advantageous performance, than widely-used graph inference (e.g., KronFit) and graph neural net baselines, at a time cost that scales linearly as the graph size $N$.

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。

↑