Variational Memory Addressing in Generative Models

Abstract

Aiming to augment generative models with external memory, we interpret the output of a memory module with stochastic addressing as a conditional mixture distribution, where a read operation corresponds to sampling a discrete memory address and retrieving the corresponding content from memory. This perspective allows us to apply variational inference to memory addressing, which enables effective training of the memory module by using the target information to guide memory lookups. Stochastic addressing is particularly well-suited for generative models as it naturally encourages multimodality which is a prominent aspect of most high-dimensional datasets. Treating the chosen address as a latent variable also allows us to quantify the amount of information gained with a memory lookup and measure the contribution of the memory module to the generative process. To illustrate the advantages of this approach we incorporate it into a variational autoencoder and apply the resulting model to the task of generative few-shot learning. The intuition behind this architecture is that the memory module can pick a relevant template from memory and the continuous part of the model can concentrate on modeling remaining variations. We demonstrate empirically that our model is able to identify and access the relevant memory contents even with hundreds of unseen Omniglot characters in memory

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Categorical Reparameterization with Gumbel-Softmax
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• DRAW: A Recurrent Neural Network For Image Generation
• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
• Improving Variational Inference with Inverse Autoregressive Flow
• Towards a Neural Statistician
• Variational inference for Monte Carlo objectives
• Reinforcement Learning Neural Turing Machines - Revised
• Generative Temporal Models with Memory
• Reweighted Wake-Sleep
• Fast Adaptation in Generative Models with Generative Matching Networks

Cited by in corpus (5)

• Hierarchical Quantized Autoencoders
• SimulLR: Simultaneous Lip Reading Transducer with Attention-Guided Adaptive Memory
• ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE
• NeurInt : Learning to Interpolate through Neural ODEs
• Physical discovery in representation learning via conditioning on prior knowledge: applications for ferroelectric domain dynamics