LINC: Decoupling Local Consequence Scoring from Hidden Matching in Constructive Neural Routing

TL;DR

LINC introduces a novel neural routing architecture that explicitly models local consequences, improving solution quality for vehicle routing and TSP problems by decoupling consequence scoring from hidden matching.

Contribution

It proposes LINC, a decoder-side candidate decision architecture that explicitly computes local consequences, enhancing neural routing performance over prior methods.

Findings

LINC reduces Solomon/Homberger gaps in CVRPTW from 13.83 extbackslash extbackslash 38.15 extbackslash extbackslash to 7.26 extbackslash extbackslash 14.71 extbackslash extbackslash.

LINC improves external-benchmark gaps for TSP and CVRP.

LINC preserves standard global matching while explicitly modeling local consequences.

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.