報告題目：Asymptotic minimax risk of stochastic block model for community extraction
報 告 人：劉秉輝 教授
所在單位：東北師範大學
報告時間：2022年8月17日 星期三 14:00-15:00
報告地點：騰訊會議 ID：726-117-696
校内聯系人：程建華 chengjh@jlu.edu.cn
報告摘要：Most existing community discovery methods focus on partitioning all nodes of the network into communities. However, many real networks contain background nodes that do not belong to any communities. In such a situation, typical methods tend to artificially split the background nodes and group them together with communities with relatively stronger connection, hence lead to distorted results. To avoid this, some community extraction methods have been developed to achieve community discovery with background nodes. There are two limitations of the existing methods for community extraction: first, they have difficulties in handling large-scale networks due to high computational complexity; second, some theoretical results, such as the minimax risk, of these community extraction models need to be further investigated. Motivated by the situation, we establish the asymptotic minimax risk of the stochastic block model for community extraction. We also propose a refinement algorithm with polynomial complexity to achieve fast computation for community extraction. Further, we illustrate that the community structure estimated by the proposed algorithm obtain the established asymptotic minimax risk. We illustrate the advantages and feasibility of the proposed algorithm via extensive simulated networks and a political blog network.
報告人簡介：劉秉輝，東北師範大學，教授、博導，統計系主任；研究方向為應用統計、機器學習和網絡數據分析；在統計學、計算機&人工智能、計量經濟學領域期刊發表SCI論文二十餘篇，部分成果發表在：統計學頂級期刊Journal of the American Statistical Association、Annals of Statistics，計算機&人工智能頂級期刊Artificial Intelligence、Journal of Machine Learning Research，計量經濟學頂級期刊Journal of Econometrics；以及領域重要期刊Journal of Business & Economic Statistics、Annals of Applied Statistics等；入選國家天元數學東北中心優秀青年學者獎勵計劃、吉林省拔尖創新人才；主持國家自然科學基金面上項目2項，參與國家自然科學基金重點項目、科技部重點研發計劃項目。
