Information-Theoretic Active Correlation Clustering
This work addresses the challenge of clustering with incomplete similarity data for applications in data analysis, but it appears incremental as it builds on existing active learning and correlation clustering methods.
The paper tackles the problem of correlation clustering with unknown pairwise similarities by using active learning to query similarities cost-efficiently, proposing information-theoretic acquisition functions based on entropy and information gain, and demonstrates superior performance compared to alternatives in various settings.
We study correlation clustering where the pairwise similarities are not known in advance. For this purpose, we employ active learning to query pairwise similarities in a cost-efficient way. We propose a number of effective information-theoretic acquisition functions based on entropy and information gain. We extensively investigate the performance of our methods in different settings and demonstrate their superior performance compared to the alternatives.