Spatial Mixture-of-ExpertsDownload PDF

Published: 31 Oct 2022, 18:00, Last Modified: 19 Dec 2022, 07:11NeurIPS 2022 AcceptReaders: Everyone
Keywords: deep learning, mixture of experts, regression, weather prediction
TL;DR: A neural network layer that learns location-dependent structure
Abstract: Many data have an underlying dependence on spatial location; it may be weather on the Earth, a simulation on a mesh, or a registered image. Yet this feature is rarely taken advantage of, and violates common assumptions made by many neural network layers, such as translation equivariance. Further, many works that do incorporate locality fail to capture fine-grained structure. To address this, we introduce the Spatial Mixture-of-Experts (SMoE) layer, a sparsely-gated layer that learns spatial structure in the input domain and routes experts at a fine-grained level to utilize it. We also develop new techniques to train SMoEs, including a self-supervised routing loss and damping expert errors. Finally, we show strong results for SMoEs on numerous tasks, and set new state-of-the-art results for medium-range weather prediction and post-processing ensemble weather forecasts.
Supplementary Material: zip
15 Replies

Loading