MVMoE: Multi-task vehicle routing solver with mixture-of-experts
Learning to solve vehicle routing problems (VRPs) has garnered much attention. However, most neural solvers are only structured and trained independently on a specific problem, making them less generic and practical. In this paper, we aim to develop a unified neural solver that can cope with a range...
Saved in:
Main Authors: | , , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9333 https://ink.library.smu.edu.sg/context/sis_research/article/10333/viewcontent/2405.01029v2.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-10333 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-103332024-09-26T07:28:05Z MVMoE: Multi-task vehicle routing solver with mixture-of-experts ZHOU, Jianan CAO, Zhiguang WU, Yaoxin SONG, Wen MA, Yining ZHANG, Jie XU, Chi Learning to solve vehicle routing problems (VRPs) has garnered much attention. However, most neural solvers are only structured and trained independently on a specific problem, making them less generic and practical. In this paper, we aim to develop a unified neural solver that can cope with a range of VRP variants simultaneously. Specifically, we propose a multi-task vehicle routing solver with mixture-of-experts (MVMoE), which greatly enhances the model capacity without a proportional increase in computation. We further develop a hierarchical gating mechanism for the MVMoE, delivering a good trade-off between empirical performance and computational complexity. Experimentally, our method significantly promotes zero-shot generalization performance on 10 unseen VRP variants, and showcases decent results on the few-shot setting and real-world benchmark instances. We further conduct extensive studies on the effect of MoE configurations in solving VRPs, and observe the superiority of hierarchical gating when facing out-of-distribution data. The source code is available at: https://github.com/RoyalSkye/Routing-MVMoE. 2024-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9333 https://ink.library.smu.edu.sg/context/sis_research/article/10333/viewcontent/2405.01029v2.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 Artificial Intelligence and Robotics |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Artificial Intelligence and Robotics |
spellingShingle |
Artificial Intelligence and Robotics ZHOU, Jianan CAO, Zhiguang WU, Yaoxin SONG, Wen MA, Yining ZHANG, Jie XU, Chi MVMoE: Multi-task vehicle routing solver with mixture-of-experts |
description |
Learning to solve vehicle routing problems (VRPs) has garnered much attention. However, most neural solvers are only structured and trained independently on a specific problem, making them less generic and practical. In this paper, we aim to develop a unified neural solver that can cope with a range of VRP variants simultaneously. Specifically, we propose a multi-task vehicle routing solver with mixture-of-experts (MVMoE), which greatly enhances the model capacity without a proportional increase in computation. We further develop a hierarchical gating mechanism for the MVMoE, delivering a good trade-off between empirical performance and computational complexity. Experimentally, our method significantly promotes zero-shot generalization performance on 10 unseen VRP variants, and showcases decent results on the few-shot setting and real-world benchmark instances. We further conduct extensive studies on the effect of MoE configurations in solving VRPs, and observe the superiority of hierarchical gating when facing out-of-distribution data. The source code is available at: https://github.com/RoyalSkye/Routing-MVMoE. |
format |
text |
author |
ZHOU, Jianan CAO, Zhiguang WU, Yaoxin SONG, Wen MA, Yining ZHANG, Jie XU, Chi |
author_facet |
ZHOU, Jianan CAO, Zhiguang WU, Yaoxin SONG, Wen MA, Yining ZHANG, Jie XU, Chi |
author_sort |
ZHOU, Jianan |
title |
MVMoE: Multi-task vehicle routing solver with mixture-of-experts |
title_short |
MVMoE: Multi-task vehicle routing solver with mixture-of-experts |
title_full |
MVMoE: Multi-task vehicle routing solver with mixture-of-experts |
title_fullStr |
MVMoE: Multi-task vehicle routing solver with mixture-of-experts |
title_full_unstemmed |
MVMoE: Multi-task vehicle routing solver with mixture-of-experts |
title_sort |
mvmoe: multi-task vehicle routing solver with mixture-of-experts |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2024 |
url |
https://ink.library.smu.edu.sg/sis_research/9333 https://ink.library.smu.edu.sg/context/sis_research/article/10333/viewcontent/2405.01029v2.pdf |
_version_ |
1814047912346255360 |