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.

翻译：我们提出了一种在高斯因子图中进行学习的方法。我们将所有相关量（输入、输出、参数、隐变量）视为图模型中的随机变量，并将训练和预测均视为具有不同观测节点的推理问题。实验表明，这些问题可通过置信传播（BP）高效求解，其更新过程本质上是局部的，为分布式和异步训练提供了令人兴奋的机会。该方法可扩展至深层网络，并提供了一种进行持续学习的自然方式：将当前任务经BP估计的参数边缘分布作为下一任务的参数先验。在视频去噪任务中，我们验证了可学习参数相对于传统因子图方法的优势，并在持续图像分类任务中展示了深度因子图的良好性能。