LongRetriever: Towards Ultra-Long Sequence based Candidate Retrieval for Recommendation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ren, Qin, Chai, Zheng, Xiao, Xijun, Zheng, Yuchao, Wu, Di
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911118485618688
author Ren, Qin
Chai, Zheng
Xiao, Xijun
Zheng, Yuchao
Wu, Di
author_facet Ren, Qin
Chai, Zheng
Xiao, Xijun
Zheng, Yuchao
Wu, Di
contents Precisely modeling user ultra-long sequences is critical for industrial recommender systems. Current approaches predominantly focus on leveraging ultra-long sequences in the ranking stage, whereas research for the candidate retrieval stage remains under-explored. This paper presents LongRetriever, a practical framework for incorporating ultra-long sequences into the retrieval stage of recommenders. Specifically, we propose in-context training and multi-context retrieval, which enable candidate-specific interaction between user sequence and candidate item, and ensure training-serving consistency under the search-based paradigm. Extensive online A/B testing conducted on a large-scale e-commerce platform demonstrates statistically significant improvements, confirming the framework's effectiveness. Currently, LongRetriever has been fully deployed in the platform, impacting billions of users.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15486
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LongRetriever: Towards Ultra-Long Sequence based Candidate Retrieval for Recommendation
Ren, Qin
Chai, Zheng
Xiao, Xijun
Zheng, Yuchao
Wu, Di
Information Retrieval
Precisely modeling user ultra-long sequences is critical for industrial recommender systems. Current approaches predominantly focus on leveraging ultra-long sequences in the ranking stage, whereas research for the candidate retrieval stage remains under-explored. This paper presents LongRetriever, a practical framework for incorporating ultra-long sequences into the retrieval stage of recommenders. Specifically, we propose in-context training and multi-context retrieval, which enable candidate-specific interaction between user sequence and candidate item, and ensure training-serving consistency under the search-based paradigm. Extensive online A/B testing conducted on a large-scale e-commerce platform demonstrates statistically significant improvements, confirming the framework's effectiveness. Currently, LongRetriever has been fully deployed in the platform, impacting billions of users.
title LongRetriever: Towards Ultra-Long Sequence based Candidate Retrieval for Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2508.15486