Multi-Task Neural Processes

TL;DR

Multi-task neural processes extend neural processes to effectively model and transfer knowledge across related tasks in multi-task learning, especially with limited data and domain shifts, showing superior performance on benchmarks.

Contribution

The paper introduces multi-task neural processes, a novel variant that leverages hierarchical Bayesian inference to incorporate shared knowledge across tasks in function space.

Findings

Effective transfer of knowledge among tasks.

Superior performance on multi-task classification.

Robustness to limited data and domain shifts.

Abstract

Neural processes have recently emerged as a class of powerful neural latent variable models that combine the strengths of neural networks and stochastic processes. As they can encode contextual data in the network's function space, they offer a new way to model task relatedness in multi-task learning. To study its potential, we develop multi-task neural processes, a new variant of neural processes for multi-task learning. In particular, we propose to explore transferable knowledge from related tasks in the function space to provide inductive bias for improving each individual task. To do so, we derive the function priors in a hierarchical Bayesian inference framework, which enables each task to incorporate the shared knowledge provided by related tasks into its context of the prediction function. Our multi-task neural processes methodologically expand the scope of vanilla neural processes and provide a new way of exploring task relatedness in function spaces for multi-task learning. The proposed multi-task neural processes are capable of learning multiple tasks with limited labeled data and in the presence of domain shift. We perform extensive experimental evaluations on several benchmarks for the multi-task regression and classification tasks. The results demonstrate the effectiveness of multi-task neural processes in transferring useful knowledge among tasks for multi-task learning and superior performance in multi-task classification and brain image segmentation.