ASP: Learn a Universal Neural Solver

Applying machine learning to combinatorial optimization problems has the potential to improve both efficiency and accuracy. However, existing learning-based solvers often struggle with generalization when faced with changes in problem distributions and scales. In this paper, we propose a new approac...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on pattern analysis and machine intelligence Ročník 46; číslo 6; s. 4102 - 4114
Hlavní autoři: Wang, Chenguang, Yu, Zhouliang, McAleer, Stephen, Yu, Tianshu, Yang, Yaodong
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.06.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Adaptation models
Combinatorial analysis
Combinatorial optimization problems
curriculum learning
generalization ability and scalability
Machine learning
Optimization
policy space response oracles
Scalability
Solvers
Training
Traveling salesman problem
Traveling salesman problems
Vehicle routing
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Applying machine learning to combinatorial optimization problems has the potential to improve both efficiency and accuracy. However, existing learning-based solvers often struggle with generalization when faced with changes in problem distributions and scales. In this paper, we propose a new approach called ASP: A daptive S taircase P olicy Space Response Oracle to address these generalization issues and learn a universal neural solver. ASP consists of two components: Distributional Exploration, which enhances the solver's ability to handle unknown distributions using Policy Space Response Oracles, and Persistent Scale Adaption, which improves scalability through curriculum learning. We have tested ASP on several challenging COPs, including the traveling salesman problem, the vehicle routing problem, and the prize collecting TSP, as well as the real-world instances from TSPLib and CVRPLib. Our results show that even with the same model size and weak training signal, ASP can help neural solvers explore and adapt to unseen distributions and varying scales, achieving superior performance. In particular, compared with the same neural solvers under a standard training pipeline, ASP produces a remarkable decrease in terms of the optimality gap with 90.9% and 47.43% on generated instances and real-world instances for TSP, and a decrease of 19% and 45.57% for CVRP.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2024.3352096