Self-Adapted Multi-Task Clustering

Abstract

Multi-task clustering improves the clustering performance of each task by transferring knowledge across related tasks. Most existing multi-task clustering methods are based on the ideal assumption that the tasks are completely related. However, in many real applications, the tasks are usually partially related, and brute-force transfer may cause negative effect which degrades the clustering performance.In this paper, we propose a self-adapted multi-task clustering (SAMTC) method which can automatically identify and transfer reusable instances among the tasks, thus avoiding negative transfer. SAMTC begins with an initialization by performing single-task clustering on each task, then executes the following three steps: first, it finds the reusable instances by measuring related clusters with Jensen-Shannon divergence between each pair of tasks, and obtains a pair of possibly related subtasks;second, it estimates the relatedness between each pair of subtasks with kernel mean matching;third, it constructs the similarity matrix for each task by exploiting useful information from the other tasks through instance transfer, and adopts spectral clustering to get the final clustering result. Experimental results on several real data sets show the superiority of the proposed algorithm over traditional single-task clustering methods and existing multitask clustering methods.