在推理时注入最新观看记录，实现无需重训练的实时推荐更新。
Inference Time Feature Injection: A Lightweight Approach for Real-Time Recommendation Freshness
- 推理时选择性替换过时用户特征，利用最近观看历史动态调整推荐。
- 关键用户指标提升0.47%，显著优于日常更新的静态推荐系统。
- 适合追求低延迟、低成本实时推荐的长视频平台使用。
许多长视频流媒体平台采用批处理训练模型和每日更新用户特征的方式，导致用户特征在一天内保持静态，无法反映最新行为，造成推荐内容陈旧。本文提出一种轻量级、模型无关的推理时特征注入方法，在不需重新训练模型的前提下，通过在推理阶段选择性地用最新观看记录覆盖过时用户特征，实现实时个性化。该方法将个性化反馈周期从日级缩短至日内级，使关键用户参与度指标提升了0.47%，在近期实验中属于最显著的增益之一。据我们所知，这是首个在长视频流媒体中证明日内个性化可带来实际影响的公开研究，为无需频繁重训练的实时推荐提供了有力替代方案。
原文摘要 · Abstract (English)
Many recommender systems in long-form video streaming reply on batch-trained models and batch-updated features, where user features are updated daily and served statically throughout the day. While efficient, this approach fails to incorporate a user's most recent actions, often resulting in stale recommendations. In this work, we present a lightweight, model-agnostic approach for intra-day personalization that selectively injects recent watch history at inference time without requiring model retraining. Our approach selectively overrides stale user features at inference time using the recent watch history, allowing the system to adapt instantly to evolving preferences. By reducing the personalization feedback loop from daily to intra-day, we observed a statistically significant 0.47% increase in key user engagement metrics which ranked among the most substantial engagement gains observed in recent experimentation cycles. To our knowledge, this is the first published evidence that intra-day personalization can drive meaningful impact in long-form video streaming service, providing a compelling alternative to full real-time architectures where model retraining is required.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。