Pareto Multi-Task Learning

TL;DR

This paper introduces Pareto MTL, a novel multi-task learning algorithm that efficiently finds a diverse set of Pareto optimal solutions, enabling better trade-offs among tasks and outperforming existing methods.

Contribution

The paper generalizes Pareto optimality in multi-task learning by proposing an algorithm that generates a well-distributed set of solutions representing various trade-offs.

Findings

Pareto MTL effectively finds diverse Pareto solutions.

The algorithm outperforms state-of-the-art methods.

Generated solutions are well-distributed and representative.

Abstract

Multi-task learning is a powerful method for solving multiple correlated tasks simultaneously. However, it is often impossible to find one single solution to optimize all the tasks, since different tasks might conflict with each other. Recently, a novel method is proposed to find one single Pareto optimal solution with good trade-off among different tasks by casting multi-task learning as multiobjective optimization. In this paper, we generalize this idea and propose a novel Pareto multi-task learning algorithm (Pareto MTL) to find a set of well-distributed Pareto solutions which can represent different trade-offs among different tasks. The proposed algorithm first formulates a multi-task learning problem as a multiobjective optimization problem, and then decomposes the multiobjective optimization problem into a set of constrained subproblems with different trade-off preferences. By solving these subproblems in parallel, Pareto MTL can find a set of well-representative Pareto optimal solutions with different trade-off among all tasks. Practitioners can easily select their preferred solution from these Pareto solutions, or use different trade-off solutions for different situations. Experimental results confirm that the proposed algorithm can generate well-representative solutions and outperform some state-of-the-art algorithms on many multi-task learning applications.