Structured Recognition for Generative Models with Explaining Away
This work addresses the challenge of integrating structured graphical models with flexible deep generative models for unsupervised learning, offering a method to reveal latent interactions in complex data like neural recordings.
The authors tackled the problem of learning structured latent representations in unsupervised learning by extending amortized variational inference to incorporate structured factors that capture posterior dependencies due to explaining away, and they demonstrated its application on synthetic data and neural spike data, where it identified latent signals correlating with behavioral covariates.
A key goal of unsupervised learning is to go beyond density estimation and sample generation to reveal the structure inherent within observed data. Such structure can be expressed in the pattern of interactions between explanatory latent variables captured through a probabilistic graphical model. Although the learning of structured graphical models has a long history, much recent work in unsupervised modelling has instead emphasised flexible deep-network-based generation, either transforming independent latent generators to model complex data or assuming that distinct observed variables are derived from different latent nodes. Here, we extend amortised variational inference to incorporate structured factors over multiple variables, able to capture the observation-induced posterior dependence between latents that results from ``explaining away'' and thus allow complex observations to depend on multiple nodes of a structured graph. We show that appropriately parametrised factors can be combined efficiently with variational message passing in rich graphical structures. We instantiate the framework in nonlinear Gaussian Process Factor Analysis, evaluating the structured recognition framework using synthetic data from known generative processes. We fit the GPFA model to high-dimensional neural spike data from the hippocampus of freely moving rodents, where the model successfully identifies latent signals that correlate with behavioural covariates.