Attentive Neural Processes

TL;DR

This paper introduces Attentive Neural Processes, enhancing Neural Processes with attention mechanisms to improve prediction accuracy, training speed, and modeling capacity for regression tasks.

Contribution

The paper proposes integrating attention into Neural Processes to address underfitting and improve their performance and flexibility.

Findings

Attention improves prediction accuracy.

Training becomes noticeably faster.

Modeling capacity is expanded.

Abstract

Neural Processes (NPs) (Garnelo et al 2018a;b) approach regression by learning to map a context set of observed input-output pairs to a distribution over regression functions. Each function models the distribution of the output given an input, conditioned on the context. NPs have the benefit of fitting observed data efficiently with linear complexity in the number of context input-output pairs, and can learn a wide family of conditional distributions; they learn predictive distributions conditioned on context sets of arbitrary size. Nonetheless, we show that NPs suffer a fundamental drawback of underfitting, giving inaccurate predictions at the inputs of the observed data they condition on. We address this issue by incorporating attention into NPs, allowing each input location to attend to the relevant context points for the prediction. We show that this greatly improves the accuracy of predictions, results in noticeably faster training, and expands the range of functions that can be modelled.