A Unified Bayesian Framework for Discriminative and Generative Continual Learning

Abhishek Kumar, Sunabha Chatterjee, Piyush Rai

Keywords: continual learning, bayesian learning

Abstract: Continual Learning is a learning paradigm where learning systems are trained on a sequence of tasks. The goal here is to perform well on the current task without suffering from a performance drop on the previous tasks. Two notable directions among the recent advances in continual learning with neural networks are (1) variational Bayes based regularization by learning priors from previous tasks, and, (2) learning the structure of deep networks to adapt to new tasks. So far, these two approaches have been orthogonal. We present a novel Bayesian framework for continual learning based on learning the structure of deep neural networks, addressing the shortcomings of both these approaches. The proposed framework learns the deep structure for each task by learning which weights to be used, and supports inter-task transfer through the overlapping of different sparse subsets of weights learned by different tasks. An appealing aspect of our proposed continual learning framework is that it is applicable to both discriminative (supervised) and generative (unsupervised) settings. Experimental results on supervised and unsupervised benchmarks shows that our model performs comparably or better than recent advances in continual learning.

One-sentence Summary: A Bayesian approach for continual learning under supervised as well as unsupervised setting, with the flexibility to adapt the model complexity as more and more tasks arrive.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=htVK0KlTE