Metraipolis › archive › dc_d8becfdfbd2d

Task-Blind No MORE: Multi-Task Information Flow in Unified Ranking Backbones — arXiv:2609.07273

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.07273
License (as archived): CC0-1.0
Archived: 2026-10-16T15:05:23.335Z
SHA-256 of the archived text: f8cdd19193118e0c33b97e56fcef9d1f149074a678c81e9d0589548767c241bd
Stable URL of this page: https://metraipolis.com/documento/dc_d8becfdfbd2d

How to cite

Task-Blind No MORE: Multi-Task Information Flow in Unified Ranking Backbones — arXiv:2609.07273 — arXiv (en), https://arxiv.org/abs/2609.07273 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d8becfdfbd2d (Metraipolis archive dc_d8becfdfbd2d, sha256 f8cdd19193118e0c33b97e56fcef9d1f149074a678c81e9d0589548767c241bd)

BibTeX

@misc{dcd8becfdfbd2d,
  title = {Task-Blind No MORE: Multi-Task Information Flow in Unified Ranking Backbones — arXiv:2609.07273},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07273},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d8becfdfbd2d; sha256 f8cdd19193118e0c33b97e56fcef9d1f149074a678c81e9d0589548767c241bd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07273. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Industrial ranking models for recommendation have scaled feature interaction and sequence modeling separately; recent architectures such as HyFormer and MixFormer unify both in a stackable backbone. Real-world recommender systems, however, nearly always require multi-task learning, yet existing unified architectures confine multi-task modeling to shallow post-backbone towers, leaving the backbone without task-aware information flow. We propose MORE (Multi-task cO-evolving Ranking modEl), which embeds multi-task information flow inside the backbone, enabling task-specific signals to co-evolve with sequence and feature representations at every layer rather than in a post-hoc fusion. It introduces Anchor Tokens that persist across backbone layers: Shared Anchors encode cross-task commonalities, while Private Anchors capture task-specific priors. In each block, Anchor Tokens (1) read task-conditioned signals from behavior sequences, (2) mix with non-sequential features under a task-boundary mask, and (3) refine per-task representations through independent branches; as blocks stack, each task obtains a differentiated representation refined through all backbone layers. Experiments on large-scale industrial datasets show that MORE consistently outperforms baselines across all tasks under comparable parameter and FLOPs budgets, and scales well with model size. Online A/B tests on Momo, a leading Chinese social discovery platform with tens of millions of monthly active users, yield 3% improvement in usage duration, 3.6% in interaction rate, and 2% in deep-chat rate. MORE is deployed in production with request-level shared computation reducing scoring latency by about 30%.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.07273 — 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 2026-10-16T14:49:33.953Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).