Class-Incremental Learning Using Generative Experience Replay Based on Time-aware Regularization
This work addresses continual learning challenges for AI systems that need to learn new tasks incrementally without access to past data, though it is incremental as it builds on existing generative replay methods.
The paper tackles the problem of class-incremental learning without forgetting by proposing a time-aware regularization method for generative experience replay, which improves memory retention and increases average performance on benchmarks under strict constraints like constant model size and no memory buffer.
Learning new tasks accumulatively without forgetting remains a critical challenge in continual learning. Generative experience replay addresses this challenge by synthesizing pseudo-data points for past learned tasks and later replaying them for concurrent training along with the new tasks' data. Generative replay is the best strategy for continual learning under a strict class-incremental setting when certain constraints need to be met: (i) constant model size, (ii) no pre-training dataset, and (iii) no memory buffer for storing past tasks' data. Inspired by the biological nervous system mechanisms, we introduce a time-aware regularization method to dynamically fine-tune the three training objective terms used for generative replay: supervised learning, latent regularization, and data reconstruction. Experimental results on major benchmarks indicate that our method pushes the limit of brain-inspired continual learners under such strict settings, improves memory retention, and increases the average performance over continually arriving tasks.