GP-ConvCNP: Better Generalization for Convolutional Conditional Neural Processes on Time Series Data

TL;DR

This paper introduces GP-ConvCNP, a model that combines Gaussian Processes with Convolutional Conditional Neural Processes to improve generalization, robustness, and sampling capabilities for time series data, especially under distribution shifts.

Contribution

The paper proposes integrating Gaussian Processes into ConvCNPs, enhancing their ability to generalize, extrapolate, and sample effectively on time series data.

Findings

Improved robustness to distribution shifts.

Enhanced extrapolation capabilities.

Maintained or improved within-distribution performance.

Abstract

Neural Processes (NPs) are a family of conditional generative models that are able to model a distribution over functions, in a way that allows them to perform predictions at test time conditioned on a number of context points. A recent addition to this family, Convolutional Conditional Neural Processes (ConvCNP), have shown remarkable improvement in performance over prior art, but we find that they sometimes struggle to generalize when applied to time series data. In particular, they are not robust to distribution shifts and fail to extrapolate observed patterns into the future. By incorporating a Gaussian Process into the model, we are able to remedy this and at the same time improve performance within distribution. As an added benefit, the Gaussian Process reintroduces the possibility to sample from the model, a key feature of other members in the NP family.