ZoRRO：零权重个人化新闻推荐系统，可扩展部署
ZoRRO: A Zero-Weight Personalized Recommender System for Scalable News Recommendation
ZoRRO 不用训练就能做新闻推荐，速度比深度学习模型快 600 多倍，点击率还差不多，特别适合大规模部署。
ZoRRO 是一种零权重、无需训练的个人化新闻推荐框架，专门面向规模化部署设计。在离线排名评估中，ZoRRO 优于多种强神经基线模型。
在线 A/B 测试中，其点击率接近最先进的深度学习模型，但速度快超过 600 倍。实验还揭示了离线与在线性能之间的差距，以及点击率相近的模型可能产生截然不同的推荐分布，进而影响整体新闻流。
这些结果将 ZoRRO 定位为大规模新闻推荐的实用高效方案。
ZoRRO: A Zero-Weight Personalized Recommender System for Scalable News Recommendation
We present ZoRRO (Zero-Weight Personalized Recommender System), a zero-weight, training-free framework for personalized news recommendation designed for scalable real-world deployment. ZoRRO outperforms strong neural baselines in offline ranking evaluations and achieves click-through rate performance in online A/B testing that is nearly on par with a state-of-the-art deep learning model, while operating more than 600 times faster. Our experiments reveal gaps between offline and online performance and demonstrate that models with similar click-through rate outcomes can produce markedly different recommendation distributions, thereby influencing the overall news flow. These findings position ZoRRO as a practical and efficient solution for large-scale news recommendation and highlight the importance of evaluating recommender systems using metrics beyond accuracy alone.
This report is categorized under AITOP's "Models" desk. Key entities and technical topics under continuous tracking include ZoRRO, 新闻推荐, 零权重, A/B测试.
Source attribution: curated from arXiv cs.LG (@Johannes Kruse, Ryotaro Shimizu, Kasper Lindskow, Jon Tofteskov, Michael Riis Andersen, Julian McAuley, Jes Frellsen).
