Posterior Meta-Replay for Continual Learning
This addresses the problem of catastrophic forgetting in continual learning for AI systems, offering a novel method that is incremental in improving Bayesian approaches.
The paper tackles the challenge of continual learning by proposing a Bayesian approach using probabilistic task-conditioned hypernetworks, termed posterior meta-replay, which compresses sequences of posterior parameter distributions with virtually no forgetting and achieves considerable performance gains over existing Bayesian methods.
Learning a sequence of tasks without access to i.i.d. observations is a widely studied form of continual learning (CL) that remains challenging. In principle, Bayesian learning directly applies to this setting, since recursive and one-off Bayesian updates yield the same result. In practice, however, recursive updating often leads to poor trade-off solutions across tasks because approximate inference is necessary for most models of interest. Here, we describe an alternative Bayesian approach where task-conditioned parameter distributions are continually inferred from data. We offer a practical deep learning implementation of our framework based on probabilistic task-conditioned hypernetworks, an approach we term posterior meta-replay. Experiments on standard benchmarks show that our probabilistic hypernetworks compress sequences of posterior parameter distributions with virtually no forgetting. We obtain considerable performance gains compared to existing Bayesian CL methods, and identify task inference as our major limiting factor. This limitation has several causes that are independent of the considered sequential setting, opening up new avenues for progress in CL.