Metraipolis › archive › dc_4d388afd55eb

MixRoute: Rethinking Single-Distribution Training for Generalizable Neural Routing — arXiv:2611.11977

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.11977
License (as archived)
CC0-1.0
Archived
2026-11-10T18:43:49.066Z
SHA-256 of the archived text
7e5956643d038bd6255ee5e38343df47fb64d50d47d84c0d357a9521ba87dee3
Stable URL of this page
https://metraipolis.com/documento/dc_4d388afd55eb

How to cite

MixRoute: Rethinking Single-Distribution Training for Generalizable Neural Routing — arXiv:2611.11977 — arXiv (en), https://arxiv.org/abs/2611.11977 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4d388afd55eb (Metraipolis archive dc_4d388afd55eb, sha256 7e5956643d038bd6255ee5e38343df47fb64d50d47d84c0d357a9521ba87dee3)
BibTeX
@misc{dc4d388afd55eb,
  title = {MixRoute: Rethinking Single-Distribution Training for Generalizable Neural Routing — arXiv:2611.11977},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.11977},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4d388afd55eb; sha256 7e5956643d038bd6255ee5e38343df47fb64d50d47d84c0d357a9521ba87dee3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11977. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural Combinatorial Optimization (NCO) is a promising paradigm for solving routing problems, yet its generalization across diverse data distributions remains a critical bottleneck. Existing methods typically tackle cross-distribution generalization through complex multi-distribution training or intricate meta-learning schemes, implicitly presuming that single-distribution training yields a weak zero-shot baseline. In this paper, we demonstrate that the potential of single-distribution training has been substantially underestimated and can be unlocked by a simple architectural inductive bias: Mix Normalization. To approach this, we first construct a comprehensive benchmark spanning three representative routing problems and 179 fine-grained datasets, capturing diverse shifts in node coordinates, customer demands, capacity and time windows. Building on this benchmark, we propose MixRoute, a neural framework that adaptively combines normalization statistics at different granularities to mitigate varying distribution shifts. Trained exclusively on uniform distributions, MixRoute generalizes effectively to a wide range of unseen distributions without any distribution-specific adaptation. Extensive experiments demonstrate that MixRoute consistently achieves state-of-the-art zero-shot generalization. Our work revisits normalization as a parsimonious alternative for zero-shot generalization against complex training-adaptation schemes.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.11977 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-10T18:37:37.670Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).