no code implementations • NeurIPS 2012 • Nan Li, Longin J. Latecki
Since the clusters of each input clustering form a partition of the dataset, the vertices corresponding to each clustering form a maximal independent set (MIS) in the attributed graph.
no code implementations • NeurIPS 2012 • Yu Zhou, Xiang Bai, Wenyu Liu, Longin J. Latecki
A key feature of our approach is that the time complexity of the dif-fusion on the TPG is the same as the diffusion process on each of the original graphs, Moreover, it is not necessary to explicitly construct the TPG in our frame-work.
no code implementations • NeurIPS 2011 • Xinggang Wang, Xiang Bai, Xingwei Yang, Wenyu Liu, Longin J. Latecki
We propose a novel inference framework for finding maximal cliques in a weighted graph that satisfy hard constraints.
no code implementations • NeurIPS 2010 • Hairong Liu, Longin J. Latecki, Shuicheng Yan
In this paper, we regard clustering as ensembles of k-ary affinity relations and clusters correspond to subsets of objects with maximal average affinity relations.
no code implementations • NeurIPS 2008 • Longin J. Latecki, Chengen Lu, Marc Sobel, Xiang Bai
It is based on a new operator, called append, that combines sets of random variables (RVs) to single RVs.