Metraipolis › archive › dc_ceaa0df87091
DP-Rec: Towards Dynamic Patching for Efficient Long-Sequence Recommendation — arXiv:2609.32215
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32215
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:59:57.927Z
- SHA-256 of the archived text
736caaa2c8a77ebe5a2e6da6f38d0e0f6d3d6f0845cbbbb13a728dc94961136e- Stable URL of this page
https://metraipolis.com/documento/dc_ceaa0df87091
How to cite
DP-Rec: Towards Dynamic Patching for Efficient Long-Sequence Recommendation — arXiv:2609.32215 — arXiv (en), https://arxiv.org/abs/2609.32215 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ceaa0df87091 (Metraipolis archive dc_ceaa0df87091, sha256 736caaa2c8a77ebe5a2e6da6f38d0e0f6d3d6f0845cbbbb13a728dc94961136e)
BibTeX
@misc{dcceaa0df87091,
title = {DP-Rec: Towards Dynamic Patching for Efficient Long-Sequence Recommendation — arXiv:2609.32215},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32215},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ceaa0df87091; sha256 736caaa2c8a77ebe5a2e6da6f38d0e0f6d3d6f0845cbbbb13a728dc94961136e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32215. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Transformers have redefined sequential recommendation by effectively modeling dynamic user behaviors and long-range dependencies. However, they remain inherently inefficient: standard architectures operate at a fixed rate, allocating comparable computation to every item in a user's history regardless of its information content. This leads to prohibitive computational overhead on long sequences and increased sensitivity to behavioral noise. To address this, practitioners often resort to lossy sequence compression, staged modeling, or truncation. This limits the model's ability to leverage the full context of long histories during inference. Inspired by the recent success of Byte Latent Transformer, we propose DP-Rec, a dynamic latent patching architecture for recommendation. DP-Rec shifts from item-level modeling to patch-level modeling by segmenting interaction sequences using contrastive entropy surprise to identify informative behavioral boundaries. A lightweight patch encoder compresses these temporally contextualized segments into a reduced set of dynamic latent behavior vectors, which are then processed by a larger latent transformer and decoded for next-item prediction. Extensive experiments show that, under constrained computational budgets, DP-Rec scales effectively to long sequences and achieves a superior efficiency-accuracy trade-off over both non-compressed and fixed-size compression baselines. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.32215 — 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 2026-10-07T20:29:02.259Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).