Controllable Pareto Multi-Task Learning

TL;DR

This paper introduces a hypernetwork-based framework for multi-task learning that allows real-time control over task trade-offs within a single model, improving efficiency and flexibility.

Contribution

It proposes a preference-conditioned multiobjective optimization approach using a hypernetwork to generate task-specific models dynamically.

Findings

Efficient real-time trade-off control among tasks.

Single model accommodates multiple preferences.

Demonstrated effectiveness across various applications.

Abstract

A multi-task learning (MTL) system aims at solving multiple related tasks at the same time. With a fixed model capacity, the tasks would be conflicted with each other, and the system usually has to make a trade-off among learning all of them together. For many real-world applications where the trade-off has to be made online, multiple models with different preferences over tasks have to be trained and stored. This work proposes a novel controllable Pareto multi-task learning framework, to enable the system to make real-time trade-off control among different tasks with a single model. To be specific, we formulate the MTL as a preference-conditioned multiobjective optimization problem, with a parametric mapping from preferences to the corresponding trade-off solutions. A single hypernetwork-based multi-task neural network is built to learn all tasks with different trade-off preferences among them, where the hypernetwork generates the model parameters conditioned on the preference. For inference, MTL practitioners can easily control the model performance based on different trade-off preferences in real-time. Experiments on different applications demonstrate that the proposed model is efficient for solving various MTL problems.