Abstract:Constructive neural routing solvers usually score the next action by matching a decoder context to candidate embeddings, hiding deterministic one-step consequences such as travel, waiting, slack, and capacity changes. We propose LINC (Local Inference via Normed Comparison), a decoder-side candidate decision architecture that computes these consequences explicitly. LINC uses them according to their decision role: centered relative consequences are compared by a shared linear local scorer, while feasible-set summaries modulate the decoder context. This preserves standard global matching and relieves the hidden state from rediscovering transition arithmetic. The Capacitated Vehicle Routing Problem with Time Windows (CVRPTW) serves as the main constrained-routing stress test; the same interface extends to the Capacitated Vehicle Routing Problem (CVRP) and Traveling Salesman Problem (TSP). In particular, for CVRPTW, LINC reduces PolyNet's Solomon/Homberger gaps from 13.83\%/38.15\% to 7.26\%/14.71\%; for TSP and CVRP, it also improves external-benchmark gaps.
| Comments: | 21 pages, 10 figures, 10 tables. Code: this https URL |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.06332 [cs.LG] |
| (or arXiv:2605.06332v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.06332 arXiv-issued DOI via DataCite (pending registration) |
From: Shaofeng Qin [view email]
[v1]
Thu, 7 May 2026 14:25:19 UTC (4,123 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。