Convolutional Conditional Neural Processes

Jonathan Gordon, Wessel P. Bruinsma, Andrew Y. K. Foong, James Requeima, Yann Dubois, Richard E. Turner

TL;DR: We extend deep sets to functional embeddings and Neural Processes to include translation equivariant members

Abstract: We introduce the Convolutional Conditional Neural Process (ConvCNP), a new member of the Neural Process family that models translation equivariance in the data. Translation equivariance is an important inductive bias for many learning problems including time series modelling, spatial data, and images. The model embeds data sets into an infinite-dimensional function space, as opposed to finite-dimensional vector spaces. To formalize this notion, we extend the theory of neural representations of sets to include functional representations, and demonstrate that any translation-equivariant embedding can be represented using a convolutional deep-set. We evaluate ConvCNPs in several settings, demonstrating that they achieve state-of-the-art performance compared to existing NPs. We demonstrate that building in translation equivariance enables zero-shot generalization to challenging, out-of-domain tasks.

Keywords: Neural Processes, Deep Sets, Translation Equivariance

Code: https://github.com/cambridge-mlg/convcnp

Community Implementations: [ 4 code implementations](https://www.catalyzex.com/paper/arxiv:1910.13556/code)