Learning in Deep Factor Graphs with Gaussian Belief Propagation
This provides a method for distributed and continual learning in deep networks, though it appears incremental as an extension of belief propagation to parameter learning.
The authors tackled the problem of learning in Gaussian factor graphs by treating all quantities as random variables and framing training and prediction as inference problems, showing that belief propagation enables efficient distributed training and achieves encouraging performance on continual image classification tasks.
We propose an approach to do learning in Gaussian factor graphs. We treat all relevant quantities (inputs, outputs, parameters, latents) as random variables in a graphical model, and view both training and prediction as inference problems with different observed nodes. Our experiments show that these problems can be efficiently solved with belief propagation (BP), whose updates are inherently local, presenting exciting opportunities for distributed and asynchronous training. Our approach can be scaled to deep networks and provides a natural means to do continual learning: use the BP-estimated parameter marginals of the current task as parameter priors for the next. On a video denoising task we demonstrate the benefit of learnable parameters over a classical factor graph approach and we show encouraging performance of deep factor graphs for continual image classification.