Efficient Continuous Pareto Exploration in Multi-Task Learning

TL;DR

This paper introduces an efficient method for continuous Pareto exploration in multi-task learning, enabling detailed analysis of trade-offs and solutions in multi-objective optimization problems with large-scale models.

Contribution

It proposes a novel approach to generate continuous Pareto sets and fronts, scaling multi-objective optimization to modern machine learning tasks with large models.

Findings

Reveals primary directions in local Pareto sets for better trade-off analysis

Finds more diverse solutions efficiently in multi-task problems

Scales well to models with millions of parameters

Abstract

Tasks in multi-task learning often correlate, conflict, or even compete with each other. As a result, a single solution that is optimal for all tasks rarely exists. Recent papers introduced the concept of Pareto optimality to this field and directly cast multi-task learning as multi-objective optimization problems, but solutions returned by existing methods are typically finite, sparse, and discrete. We present a novel, efficient method that generates locally continuous Pareto sets and Pareto fronts, which opens up the possibility of continuous analysis of Pareto optimal solutions in machine learning problems. We scale up theoretical results in multi-objective optimization to modern machine learning problems by proposing a sample-based sparse linear system, for which standard Hessian-free solvers in machine learning can be applied. We compare our method to the state-of-the-art algorithms and demonstrate its usage of analyzing local Pareto sets on various multi-task classification and regression problems. The experimental results confirm that our algorithm reveals the primary directions in local Pareto sets for trade-off balancing, finds more solutions with different trade-offs efficiently, and scales well to tasks with millions of parameters.