Unsupervised Continual Learning via Self-Adaptive Deep Clustering Approach
This addresses the problem of costly labeling and task dependency in continual learning for real-time deployment, though it appears incremental as it builds on existing clustering and replay techniques.
The paper tackles unsupervised continual learning by proposing KIERA, a self-adaptive deep clustering approach that avoids labeled data and task boundaries, achieving highly competitive performance compared to state-of-the-art methods.
Unsupervised continual learning remains a relatively uncharted territory in the existing literature because the vast majority of existing works call for unlimited access of ground truth incurring expensive labelling cost. Another issue lies in the problem of task boundaries and task IDs which must be known for model's updates or model's predictions hindering feasibility for real-time deployment. Knowledge Retention in Self-Adaptive Deep Continual Learner, (KIERA), is proposed in this paper. KIERA is developed from the notion of flexible deep clustering approach possessing an elastic network structure to cope with changing environments in the timely manner. The centroid-based experience replay is put forward to overcome the catastrophic forgetting problem. KIERA does not exploit any labelled samples for model updates while featuring a task-agnostic merit. The advantage of KIERA has been numerically validated in popular continual learning problems where it shows highly competitive performance compared to state-of-the art approaches. Our implementation is available in \textit{\url{https://github.com/ContinualAL/KIERA}}.