BooVAE: Boosting Approach for Continual Learning of VAE

TL;DR

BooVAE introduces a boosting-based continual learning method for VAEs that learns a diverse, task-specific prior to prevent catastrophic forgetting across sequential tasks, demonstrated on multiple datasets.

Contribution

It proposes a novel boosting approach to learn task-specific priors for VAEs, effectively mitigating catastrophic forgetting in continual learning scenarios.

Findings

Prevents catastrophic forgetting on MNIST, Fashion MNIST, NotMNIST, and CelebA.

Automatically adapts to new tasks with minimal components.

Outperforms existing methods in continual VAE learning.

Abstract

Variational autoencoder (VAE) is a deep generative model for unsupervised learning, allowing to encode observations into the meaningful latent space. VAE is prone to catastrophic forgetting when tasks arrive sequentially, and only the data for the current one is available. We address this problem of continual learning for VAEs. It is known that the choice of the prior distribution over the latent space is crucial for VAE in the non-continual setting. We argue that it can also be helpful to avoid catastrophic forgetting. We learn the approximation of the aggregated posterior as a prior for each task. This approximation is parametrised as an additive mixture of distributions induced by encoder evaluated at trainable pseudo-inputs. We use a greedy boosting-like approach with entropy regularisation to learn the components. This method encourages components diversity, which is essential as we aim at memorising the current task with the fewest components possible. Based on the learnable prior, we introduce an end-to-end approach for continual learning of VAEs and provide empirical studies on commonly used benchmarks (MNIST, Fashion MNIST, NotMNIST) and CelebA datasets. For each dataset, the proposed method avoids catastrophic forgetting in a fully automatic way.