• Home
  • Search
  • A First-Order Multi-Gradient Algorithm for Multi-Objective Bi-Level Optimization
  • Cite Icon4
  • https://doi.org/10.3233/faia240793Copy DOI Icon

A First-Order Multi-Gradient Algorithm for Multi-Objective Bi-Level Optimization

Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

In this paper, we study the Multi-Objective Bi-Level Optimization (MOBLO) problem, where the upper-level subproblem is a multi-objective optimization problem and the lower-level subproblem is for scalar optimization. Existing gradient-based MOBLO algorithms need to compute the Hessian matrix, causing the computational inefficient problem. To address this, we propose an efficient first-order multi-gradient method for MOBLO, called FORUM. Specifically, we reformulate MOBLO problems as a constrained multi-objective optimization (MOO) problem via the value-function approach. Then we propose a novel multi-gradient aggregation method to solve the challenging constrained MOO problem. Theoretically, we provide the complexity analysis to show the efficiency of the proposed method and a non-asymptotic convergence result. Empirically, extensive experiments demonstrate the effectiveness and efficiency of the proposed FORUM method in different learning problems. In particular, it achieves state-of-the-art performance on three multi-task learning benchmark datasets. The code is available at https://github.com/Baijiong-Lin/FORUM.

Similar Papers
  • PDF
  • Research Article
  • Citations5

Multi-Objective BiLevel Optimization by Bayesian Optimization

  • Mar 30, 2024
  • Algorithms
  • Vedat Dogan +1
  • Research Article
  • Citations14

6G shared base station planning using an evolutionary bi-level multi-objective optimization algorithm

  • May 25, 2023
  • Information Sciences
  • Kuntao Li +2
  • Conference Article
  • Citations11

Effective, Efficient and Robust Neural Architecture Search

  • Jul 18, 2022
  • Zhixiong Yue +3
  • Conference Article
  • Citations36

Transportation policy formulation as a multi-objective bilevel optimization problem

  • May 01, 2015
  • Ankur Sinha +2
  • Research Article
  • Citations20

Bi-level multi-objective combinatorial optimization using reference approximation of the lower level reaction

  • Jan 01, 2020
  • Procedia Computer Science
  • Malek Abbassi +3
  • PDF
  • Research Article
  • Citations30

Land Use Allocation Based on a Multi-Objective Artificial Immune Optimization Model: An Application in Anlu County, China

  • Nov 23, 2015
  • Sustainability
  • Xiaoya Ma +1
  • Book Chapter
  • Citations2

A Test Suite for Multi-objective Multi-fidelity Optimization

  • Jan 01, 2023
  • Angus Kenny +3
  • Research Article
  • Citations2

A Review of Research on Multi-Objective Process Parameter Optimization Technology for Grinding Machining

  • Jan 15, 2026
  • Technologies
  • Xiao Yang +5
  • Research Article
  • Citations12

Optimality conditions in terms of convexificators for a bilevel multiobjective optimization problem

  • Apr 09, 2020
  • Optimization
  • S Dempe +2
  • Book Chapter
  • Citations170

Solving Bilevel Multi-Objective Optimization Problems Using Evolutionary Algorithms

  • Jan 01, 2009
  • Kalyanmoy Deb +1
  • Research Article
  • Citations32

Necessary Optimality Conditions and a New Approach to Multiobjective Bilevel Optimization Problems

  • Mar 29, 2012
  • Journal of Optimization Theory and Applications
  • N Gadhi +1
  • Research Article
  • Citations24

Software prototype for solving multi-objective machining optimization problems: Application in non-conventional machining processes

  • Apr 12, 2014
  • Expert Systems with Applications
  • Marko Kovačević +3
  • Research Article
  • Citations199

High Performance Computing for Cyber Physical Social Systems by Using Evolutionary Multi-Objective Optimization Algorithm

  • Jan 01, 2017
  • IEEE Transactions on Emerging Topics in Computing
  • Gai-Ge Wang +4
  • Conference Article
  • Citations3

Research of a Self-adaptive Mixed-Variable Multi-objective Ant Colony Optimization Algorithm

  • Nov 01, 2020
  • Yiguang Gong +2
  • Research Article
  • Citations30

Cooperative Coevolution With Knowledge-Based Dynamic Variable Decomposition for Bilevel Multiobjective Optimization

  • Dec 01, 2022
  • IEEE Transactions on Evolutionary Computation
  • Xinye Cai +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.