arXiv cs.AI· Chi Liu, Jiangxia Cao, Rui Huang, Kuo Cai, Weifeng Ding, Qiang Luo, Kun Gai, Guorui Zhou·· 6 天前AI 评分24
快手 CRM：可控条件的检索模型
CRM: Retrieval Model with Controllable Condition
AI 导读
快手提出可控检索模型 CRM，将观看时长作为条件加入用户塔，训练时学习在给定实际观看时长下预测下一个视频，推理时直接输入目标观看时长即可调控检索，无需重训。物品塔与条件解耦，物品嵌入仍可预计算并建索引做 ANN 搜索，CRM 同时以 DNN 双塔和 Decision Transformer 实现，后者用目标观看时长作为数值提示词。
正文 · 原文
Abstract:Retrieval models for recommendation need to account for outcomes such as watch time while searching large item corpora efficiently. We present the Controllable Retrieval Model (CRM), an outcome-conditioned retrieval framework that adds watch time as an input to the user tower. During training, CRM learns to predict the next item given its observed watch time; at inference, we supply a desired watch time to steer retrieval without retraining. The item tower is independent of the condition, so item embeddings can still be precomputed and indexed for approximate nearest neighbor (ANN) search. We implement CRM as both a DNN-based two-tower model and a Decision Transformer. The Transformer interleaves item tokens with watch-time-to-go condition tokens, using the target watch time as a numerical prompt for next-item prediction. For each online request, we choose between the average and maximum watch times in the user's recent history as the condition. CRM is deployed in Kuaishou's short-video recommendation system, which serves over 400 million users. Online A/B tests show video watch time improvements of 0.372% in Kuaishou and 0.457% in Kuaishou Lite.
| Comments: | 4 pages. Revised version with improved presentation |
| Subjects: | Information Retrieval (cs.IR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2412.13844 [cs.IR] |
| (or arXiv:2412.13844v2 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2412.13844 arXiv-issued DOI via DataCite |
Submission history
From: Chi Liu [view email]
[v1]
Wed, 18 Dec 2024 13:37:36 UTC (584 KB)
[v2]
Fri, 9 Oct 2026 08:54:30 UTC (581 KB)
来源：arXiv cs.AI · arxiv.org