Adaptive Resonance Theory-based Topological Clustering with a Divisive Hierarchical Structure Capable of Continual Learning
This work addresses the need for more automated and efficient continual learning clustering methods, though it appears incremental as it builds on existing ART frameworks.
The paper tackles the problem of data-dependent manual tuning of the similarity threshold in Adaptive Resonance Theory (ART) clustering by proposing an algorithm that automatically estimates this threshold from data distribution, and it achieves high clustering performance comparable to state-of-the-art hierarchical clustering algorithms.
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.