Bhattacharya, Indrajit and Godbole, Shantanu and Joshi, Sachindra and Verma, Ashish (2012) Cross-Guided Clustering: Transfer of Relevant Supervision across Tasks. In: ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 6 (2).
PDF
acm_tkdd_6-2_2012.pdf - Published Version Restricted to Registered users only Download (586kB) | Request a copy |
Abstract
Lack of supervision in clustering algorithms often leads to clusters that are not useful or interesting to human reviewers. We investigate if supervision can be automatically transferred for clustering a target task, by providing a relevant supervised partitioning of a dataset from a different source task. The target clustering is made more meaningful for the human user by trading-off intrinsic clustering goodness on the target task for alignment with relevant supervised partitions in the source task, wherever possible. We propose a cross-guided clustering algorithm that builds on traditional k-means by aligning the target clusters with source partitions. The alignment process makes use of a cross-task similarity measure that discovers hidden relationships across tasks. When the source and target tasks correspond to different domains with potentially different vocabularies, we propose a projection approach using pivot vocabularies for the cross-domain similarity measure. Using multiple real-world and synthetic datasets, we show that our approach improves clustering accuracy significantly over traditional k-means and state-of-the-art semi-supervised clustering baselines, over a wide range of data characteristics and parameter settings.
Item Type: | Journal Article |
---|---|
Publication: | ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA |
Publisher: | ASSOC COMPUTING MACHINERY |
Additional Information: | Copyright for this article belongs to the ACM |
Keywords: | Multitask; transfer; cluster alignment |
Department/Centre: | Division of Electrical Sciences > Computer Science & Automation |
Date Deposited: | 17 Sep 2012 10:34 |
Last Modified: | 17 Sep 2012 10:34 |
URI: | http://eprints.iisc.ac.in/id/eprint/45067 |
Actions (login required)
View Item |