Lifelong Mixture of Variational Autoencoders

Abstract

In this paper, we propose an end-to-end lifelong learning mixture of experts. Each expert is implemented by a Variational Autoencoder (VAE). The experts in the mixture system are jointly trained by maximizing a mixture of individual component evidence lower bounds (MELBO) on the log-likelihood of the given training samples. The mixing coefficients in the mixture, control the contributions of each expert in the goal representation. These are sampled from a Dirichlet distribution whose parameters are determined through non-parametric estimation during lifelong learning. The model can learn new tasks fast when these are similar to those previously learnt. The proposed Lifelong mixture of VAE (L-MVAE) expands its architecture with new components when learning a completely new task. After the training, our model can automatically determine the relevant expert to be used when fed with new data samples. This mechanism benefits both the memory efficiency and the required computational cost as only one expert is used during the inference. The L-MVAE inference model is able to perform interpolation in the joint latent space across the data domains associated with different tasks and is shown to be efficient for disentangled learning representation.

Accepted by IEEE Transactions on Neural Networks and Learning Systems

References in corpus (12)

• Distilling the Knowledge in a Neural Network
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Efficient Lifelong Learning with A-GEM
• Three scenarios for continual learning
• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
• On Tiny Episodic Memories in Continual Learning
• Less-forgetting Learning in Deep Neural Networks
• BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning
• Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models
• Continual Unsupervised Representation Learning
• Lifelong Teacher-Student Network Learning
• Symmetric Variational Autoencoder and Connections to Adversarial Learning