A3S: A General Active Clustering Method with Pairwise Constraints

TL;DR

This paper introduces A3S, a novel active clustering framework that adaptively improves clustering quality and reduces human query costs by strategically adjusting initial clusters based on information theory insights.

Contribution

A3S is a new adaptive clustering method that enhances active clustering by integrating a cluster adjustment scheme inspired by information theory, improving scalability and reducing query costs.

Findings

A3S outperforms existing methods in clustering quality.

A3S requires fewer human queries for comparable results.

A3S demonstrates scalability on large, real-world datasets.

Abstract

Active clustering aims to boost the clustering performance by integrating human-annotated pairwise constraints through strategic querying. Conventional approaches with semi-supervised clustering schemes encounter high query costs when applied to large datasets with numerous classes. To address these limitations, we propose a novel Adaptive Active Aggregation and Splitting (A3S) framework, falling within the cluster-adjustment scheme in active clustering. A3S features strategic active clustering adjustment on the initial cluster result, which is obtained by an adaptive clustering algorithm. In particular, our cluster adjustment is inspired by the quantitative analysis of Normalized mutual information gain under the information theory framework and can provably improve the clustering quality. The proposed A3S framework significantly elevates the performance and scalability of active clustering. In extensive experiments across diverse real-world datasets, A3S achieves desired results with significantly fewer human queries compared with existing methods.