Metraipolis › archive › dc_eeefb486bbbe

MARS: Multi-resolution Adaptive Routing for Sequential Recommendation — arXiv:2610.07505

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.07505
License (as archived): CC0-1.0
Archived: 2026-10-07T11:18:43.624Z
SHA-256 of the archived text: ad02850d01dfadbc3f0a9f66eaca7206548d4c4877ffbd64d2cd6aa7043c3bd1
Stable URL of this page: https://metraipolis.com/documento/dc_eeefb486bbbe

How to cite

MARS: Multi-resolution Adaptive Routing for Sequential Recommendation — arXiv:2610.07505 — arXiv (en), https://arxiv.org/abs/2610.07505 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eeefb486bbbe (Metraipolis archive dc_eeefb486bbbe, sha256 ad02850d01dfadbc3f0a9f66eaca7206548d4c4877ffbd64d2cd6aa7043c3bd1)

BibTeX

@misc{dceeefb486bbbe,
  title = {MARS: Multi-resolution Adaptive Routing for Sequential Recommendation — arXiv:2610.07505},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07505},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eeefb486bbbe; sha256 ad02850d01dfadbc3f0a9f66eaca7206548d4c4877ffbd64d2cd6aa7043c3bd1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07505. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-history recommenders often compress each user's history into a compact, candidate-independent memory that is cached and reused to score large candidate pools. We show that real user histories exhibit multi-scale semantic structure, with short-lived intent, medium-term interests, and long-term preferences coexisting in one sequence, and that monolithic cached memories preserve these scales unevenly: linear probes recover recent and mid-range content far worse than long-range content. We call this failure mode \textit{temporal aliasing}. We propose \textbf{MARS}, a multi-resolution user memory that writes the full history into recurrent state tracks anchored to different half-lives, and a sparse routing reader that materializes compact seed memories by selecting the relevant temporal resolutions for each seed, preserving fixed-size candidate scoring. MARS outperforms strong baselines on three public datasets, with gains that grow with history length. Component-matched ablations with paired tests show that temporal diversity and selective routing each contribute beyond what hard-window memories or added capacity provide. The advantage of MARS over its interface-matched baseline also widens after within-user behavioral shifts, at about $1.02\times$ that baseline's warm-cache serving latency for $1{,}000$ candidates per user.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.07505 — 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 2026-10-07T11:15:24.514Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).