Adaptive Resonance Theory-based Topological Clustering with a Divisive Hierarchical Structure Capable of Continual Learning

TL;DR

This paper introduces an ART-based topological clustering algorithm with automatic threshold estimation and a hierarchical structure, enabling effective continual learning and high clustering performance.

Contribution

It presents a novel ART-based clustering method that automatically determines similarity thresholds and incorporates a divisive hierarchical structure for continual learning.

Findings

Achieves clustering performance comparable to state-of-the-art algorithms.

Automatically estimates similarity thresholds from data distribution.

Supports continual learning with hierarchical structure.

Abstract

Adaptive Resonance Theory (ART) is considered as an effective approach for realizing continual learning thanks to its ability to handle the plasticity-stability dilemma. In general, however, the clustering performance of ART-based algorithms strongly depends on the specification of a similarity threshold, i.e., a vigilance parameter, which is data-dependent and specified by hand. This paper proposes an ART-based topological clustering algorithm with a mechanism that automatically estimates a similarity threshold from the distribution of data points. In addition, for improving information extraction performance, a divisive hierarchical clustering algorithm capable of continual learning is proposed by introducing a hierarchical structure to the proposed algorithm. Experimental results demonstrate that the proposed algorithm has high clustering performance comparable with recently-proposed state-of-the-art hierarchical clustering algorithms.