Information Bottleneck Co-clustering

Co-clustering has emerged as an important approach for mining contingency data matrices. We present a novel approach to co-clustering based on the Information Bottleneck principle, called Information Bottleneck Co-clustering (IBCC), which supports both soft-partition and hardpartition co-clusterings, and leverages an annealing-style strategy to bypass local optima. Existing co-clustering methods require the user to define the number of rowand column-clusters respectively. In practice, though, the number of rowand column-clusters may not be independent. To address this issue, we also present an agglomerative Information Bottleneck Co-clustering (aIBCC) approach, which automatically captures the relation between the numbers of clusters. The experimental results demonstrate the effectiveness and efficiency of our techniques.