Variational Continual Learning

Cuong V. Nguyen, Yingzhen Li, Thang D. Bui, Richard E. Turner

Abstract: This paper develops variational continual learning (VCL), a simple but general framework for continual learning that fuses online variational inference (VI) and recent advances in Monte Carlo VI for neural networks. The framework can successfully train both deep discriminative models and deep generative models in complex continual learning settings where existing tasks evolve over time and entirely new tasks emerge. Experimental results show that VCL outperforms state-of-the-art continual learning methods on a variety of tasks, avoiding catastrophic forgetting in a fully automatic way.

TL;DR: This paper develops a principled method for continual learning in deep models.

Keywords: continual learning, online variational inference

Code: [ 8 community implementations](https://paperswithcode.com/paper/?openreview=BkQqq0gRb)

Data: [Permuted MNIST](https://paperswithcode.com/dataset/permuted-mnist)

Community Implementations: [ 4 code implementations](https://www.catalyzex.com/paper/variational-continual-learning/code)