Neural multi-objective combinatorial optimization with diversity enhancement
Most of existing neural methods for multi-objective combinatorial optimization (MOCO) problems solely rely on decomposition, which often leads to repetitive solutions for the respective subproblems, thus a limited Pareto set. Beyond decomposition, we propose a novel neural heuristic with diversity e...
Saved in:
Main Authors: | , , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8402 https://ink.library.smu.edu.sg/context/sis_research/article/9405/viewcontent/2310.15195.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-9405 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-94052024-01-09T03:50:35Z Neural multi-objective combinatorial optimization with diversity enhancement CHEN, Jinbiao ZHANG, Zizhen CAO, Zhiguang WU, Yaoxin MA, Yining YE, Te WANG, Jiahai Most of existing neural methods for multi-objective combinatorial optimization (MOCO) problems solely rely on decomposition, which often leads to repetitive solutions for the respective subproblems, thus a limited Pareto set. Beyond decomposition, we propose a novel neural heuristic with diversity enhancement (NHDE) to produce more Pareto solutions from two perspectives. On the one hand, to hinder duplicated solutions for different subproblems, we propose an indicator-enhanced deep reinforcement learning method to guide the model, and design a heterogeneous graph attention mechanism to capture the relations between the instance graph and the Pareto front graph. On the other hand, to excavate more solutions in the neighborhood of each subproblem, we present a multiple Pareto optima strategy to sample and preserve desirable solutions. Experimental results on classic MOCO problems show that our NHDE is able to generate a Pareto front with higher diversity, thereby achieving superior overall performance. Moreover, our NHDE is generic and can be applied to different neural methods for MOCO. 2023-12-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8402 https://ink.library.smu.edu.sg/context/sis_research/article/9405/viewcontent/2310.15195.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Databases and Information Systems |
spellingShingle |
Databases and Information Systems CHEN, Jinbiao ZHANG, Zizhen CAO, Zhiguang WU, Yaoxin MA, Yining YE, Te WANG, Jiahai Neural multi-objective combinatorial optimization with diversity enhancement |
description |
Most of existing neural methods for multi-objective combinatorial optimization (MOCO) problems solely rely on decomposition, which often leads to repetitive solutions for the respective subproblems, thus a limited Pareto set. Beyond decomposition, we propose a novel neural heuristic with diversity enhancement (NHDE) to produce more Pareto solutions from two perspectives. On the one hand, to hinder duplicated solutions for different subproblems, we propose an indicator-enhanced deep reinforcement learning method to guide the model, and design a heterogeneous graph attention mechanism to capture the relations between the instance graph and the Pareto front graph. On the other hand, to excavate more solutions in the neighborhood of each subproblem, we present a multiple Pareto optima strategy to sample and preserve desirable solutions. Experimental results on classic MOCO problems show that our NHDE is able to generate a Pareto front with higher diversity, thereby achieving superior overall performance. Moreover, our NHDE is generic and can be applied to different neural methods for MOCO. |
format |
text |
author |
CHEN, Jinbiao ZHANG, Zizhen CAO, Zhiguang WU, Yaoxin MA, Yining YE, Te WANG, Jiahai |
author_facet |
CHEN, Jinbiao ZHANG, Zizhen CAO, Zhiguang WU, Yaoxin MA, Yining YE, Te WANG, Jiahai |
author_sort |
CHEN, Jinbiao |
title |
Neural multi-objective combinatorial optimization with diversity enhancement |
title_short |
Neural multi-objective combinatorial optimization with diversity enhancement |
title_full |
Neural multi-objective combinatorial optimization with diversity enhancement |
title_fullStr |
Neural multi-objective combinatorial optimization with diversity enhancement |
title_full_unstemmed |
Neural multi-objective combinatorial optimization with diversity enhancement |
title_sort |
neural multi-objective combinatorial optimization with diversity enhancement |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2023 |
url |
https://ink.library.smu.edu.sg/sis_research/8402 https://ink.library.smu.edu.sg/context/sis_research/article/9405/viewcontent/2310.15195.pdf |
_version_ |
1787590769512546304 |