A Framework for Controllable Pareto Front Learning with Completed Scalarization Functions and its Applications

2023/02/24 by Tuan, Tran Anh, Long P. Hoang, Hoang, Long P. +4 · 2 citations
Computer Science · #Advanced Multi-Objective Optimization Algorithms #FOS: Mathematics #Machine Learning and Data Classification #Metaheuristic Optimization Algorithms Research #Optimization and Control (math.OC)

paper · pdf · doi:10.48550/arxiv.2302.12487

openalex publication_date 2023/02/24 · openalex created_date 2023/03/01 · openalex updated_date 2026/07/28

Abstract

Pareto Front Learning (PFL) was recently introduced as an efficient method for approximating the entire Pareto front, the set of all optimal solutions to a Multi-Objective Optimization (MOO) problem. In the previous work, the mapping between a preference vector and a Pareto optimal solution is still ambiguous, rendering its results. This study demonstrates the convergence and completion aspects of solving MOO with pseudoconvex scalarization functions and combines them into Hypernetwork in order to offer a comprehensive framework for PFL, called Controllable Pareto Front Learning. Extensive experiments demonstrate that our approach is highly accurate and significantly less computationally expensive than prior methods in term of inference time.

Cited by

• Identifying Offline Metrics that Predict Online Impact: A Pragmatic Strategy for Real-World Recommender Systems
• A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworks

Related

• Learning the Pareto Front with Hypernetworks
• Improving Pareto Front Learning via Multi-Sample Hypernetworks
• Scalable Unidirectional Pareto Optimality for Multi-Task Learning with\n Constraints
• Scalable Pareto Front Approximation for Deep Multi-Objective Learning
• Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated Learning