.png){kind=icon}
返回
A convergence theorem for graph shift-type algorithms
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2015.02.013.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The Robust Graph mode seeking by Graph Shift (Liu and Tan, 2010) (RGGS) algorithm represents a recent promising approach for discovering dense subgraphs in noisy data. However, there are no theoretical foundations for proving the convergence of the RGGS algorithm, leaving the question as to whether an algorithm works for solid reasons. In this paper, we propose a generic theoretical framework consisting of three key Graph Shift (GS) components: the simplex of a generated sequence set, the monotonic and continuous objective function and closed mapping. We prove that the GS-type algorithms built on such components can be transformed to fit Zangwill's theory, and the sequence set generated by the GS procedures always terminates at a local maximum, or at worst, contains a subsequence which converges to a local maximum of the similarity measure function. The framework is verified by theoretical analysis and experimental results of several typical GS-type algorithms. (C) 2015 Elsevier Ltd. All rights reserved.
Keyword:
Convergence proof
The Robust Graph mode seeking by Graph
Shift (RGGS) algorithm
Dominant Sets
Pairwise Clustering
Zangwill's theory
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
.png){kind=icon}
分享收藏Development of top-level requirements for regional aircraft based on the needs of the Russian marketOAAI
OAAI分享收藏分享收藏Separation by dielectrophoresis of dormant and nondormant bacterial cells of Mycobacterium smegmatisOAAI
OAAI分享收藏
查看更多内容