Memory-efficient Continual Learning with Prototypical Exemplar Condensation

arXiv:2603.13804v2 Announce Type: replace-cross Abstract: Rehearsal-based continual learning (CL) mitigates catastrophic forgetting by maintaining a subset of samples from previous tasks for replay. Existing studies primarily focus on optimizing memory storage through coreset selection strategies. While these methods are effective, they typically require storing a substantial number of samples per class (SPC), often exceeding 20, to maintain satisfactory performance. In this work, we propose to further compress the memory footprint by synthesizing and storing prototypical exemplars, which can form representative prototypes when passed through the feature extractor. Owing to their representative nature, these exemplars enable the model to retain previous knowledge using only a small number of samples while preserving privacy. Moreover, we introduce a perturbation-based augmentation mechanism that generates synthetic variants of previous data during training, thereby enhancing CL performance. Extensive evaluations on widely used benchmark datasets and settings demonstrate that the proposed algorithm achieves superior performance compared to existing baselines, particularly in scenarios involving large-scale datasets and a high number of tasks.

Related

• Information as Structural Alignment: A Dynamical Theory of Continual Learning
• Continual Visual Anomaly Detection on the Edge: Benchmark and Efficient Solutions
• LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization
• Toward Memory-Aided World Models: Benchmarking via Spatial Consistency

Source: arXiv cs.AI | 2026-04-13