Learning to solve routing problems via distributionally robust optimization

• Main Authors: YUAN, Jiang, WU, Yaoxin, CAO, Zhiguang
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Benchmark datasets; Convolutional neural network; Generalization ability; Generalization performance; Learn+; Module-based; Original model; Robust optimization; Routing problems; Synthesised; Software Engineering; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/8162; https://ink.library.smu.edu.sg/context/sis_research/article/9165/viewcontent/Learning_to_Solve_Routing_Problems_via_Distributionally_Robust_Optimization.pdf
• Institution: Singapore Management University

Recent deep models for solving routing problems always assume a single distribution of nodes for training, which severely impairs their cross-distribution generalization ability. In this paper, we exploit group distributionally robust optimization (group DRO) to tackle this issue, where we jointly o...