Improving Pareto Front Learning via Multi-Sample Hypernetworks

TL;DR

This paper introduces PHN-HVI, a hypernetwork-based framework for Pareto Front Learning that generates multiple solutions to improve the quality of the Pareto front in multi-objective optimization tasks.

Contribution

The paper proposes a novel PFL framework using hypernetworks to generate diverse solutions and maximize hypervolume, addressing limitations of existing methods.

Findings

Significantly outperforms baselines in producing Pareto fronts.

Effectively generates diverse solutions for multi-objective problems.

Enhances Pareto front quality by leveraging hypervolume maximization.

Abstract

Pareto Front Learning (PFL) was recently introduced as an effective approach to obtain a mapping function from a given trade-off vector to a solution on the Pareto front, which solves the multi-objective optimization (MOO) problem. Due to the inherent trade-off between conflicting objectives, PFL offers a flexible approach in many scenarios in which the decision makers can not specify the preference of one Pareto solution over another, and must switch between them depending on the situation. However, existing PFL methods ignore the relationship between the solutions during the optimization process, which hinders the quality of the obtained front. To overcome this issue, we propose a novel PFL framework namely PHN-HVI, which employs a hypernetwork to generate multiple solutions from a set of diverse trade-off preferences and enhance the quality of the Pareto front by maximizing the Hypervolume indicator defined by these solutions. The experimental results on several MOO machine learning tasks show that the proposed framework significantly outperforms the baselines in producing the trade-off Pareto front.