Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates

Abstract

Background: Catastrophic forgetting is the notorious vulnerability of neural networks to the changes in the data distribution during learning. This phenomenon has long been considered a major obstacle for using learning agents in realistic continual learning settings. A large body of continual learning research assumes that task boundaries are known during training. However, only a few works consider scenarios in which task boundaries are unknown or not well defined -- task agnostic scenarios. The optimal Bayesian solution for this requires an intractable online Bayes update to the weights posterior. Contributions: We aim to approximate the online Bayes update as accurately as possible. To do so, we derive novel fixed-point equations for the online variational Bayes optimization problem, for multivariate Gaussian parametric distributions. By iterating the posterior through these fixed-point equations, we obtain an algorithm (FOO-VB) for continual learning which can handle non-stationary data distribution using a fixed architecture and without using external memory (i.e. without access to previous data). We demonstrate that our method (FOO-VB) outperforms existing methods in task agnostic scenarios. FOO-VB Pytorch implementation will be available online.

arXiv commentThe arXiv paper "Task Agnostic Continual Learning Using Online Variational Bayes" is a preliminary pre-print of this paper. The main differences between the versions are: 1. We develop new algorithmic framework (FOO-VB). 2. We add multivariate Gaussian and matrix variate Gaussian versions of the algorithm. 3. We demonstrate the new algorithm performance in task agnostic scenarios

References in corpus (23)

• Overcoming catastrophic forgetting in neural networks
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Weight Uncertainty in Neural Networks
• Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
• Continual Learning Through Synaptic Intelligence
• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
• Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
• Optimizing Neural Networks with Kronecker-factored Approximate Curvature
• Variational Continual Learning
• Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines
• Bayesian Dark Knowledge
• Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
• Streaming Variational Bayes
• Continual Unsupervised Representation Learning
• Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies
• Task Agnostic Continual Learning Using Online Variational Bayes
• Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam
• Task Agnostic Continual Learning via Meta Learning
• Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL
• Noisy Natural Gradient as Variational Inference
• Overpruning in Variational Bayesian Neural Networks
• On Catastrophic Forgetting and Mode Collapse in Generative Adversarial Networks

Cited by in corpus (1)

• Posterior Meta-Replay for Continual Learning