arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.05475cs.IR
收藏

大规模Top-N推荐中基于二进制编码的候选生成算法

Candidate Generation with Binary Codes for Large-Scale Top-N Recommendation

Wang-Cheng Kang, Julian McAuley

摘要:

从大型语料库中生成前N个推荐对于大规模执行来说是计算昂贵的。在工业环境中,通常采用基于候选生成和重新排序的方法来缓解效率问题。然而,仍有待充分研究如何以及这些计划近似完整的排名(或需要多少候选人才能实现良好的近似),或开发系统的方法来有效地产生高质量的候选人。在本文中,我们试图调查这些问题,通过提出一个基于候选生成和重新排名的框架(CIGAR),它首先学习一个偏好保持二进制嵌入构建一个哈希表检索候选人,然后学习重新排名的候选人使用实值排名模型与面向候选人的目标。我们对由数百万用户/项目和数亿交互组成的几个大规模真实数据集进行了全面的研究。我们的研究结果表明,CIGAR显着提高了Top-N的准确性,对国家的最先进的推荐模型,同时减少查询时间的数量级。我们希望这项工作可以引起更多的关注,在推荐系统中的候选生成问题。

英文摘要:

Generating the Top-N recommendations from a large corpus is computationally expensive to perform at scale. Candidate generation and re-ranking based approaches are often adopted in industrial settings to alleviate efficiency problems. However it remains to be fully studied how well such schemes approximate complete rankings (or how many candidates are required to achieve a good approximation), or to develop systematic approaches to generate high-quality candidates efficiently. In this paper, we seek to investigate these questions via proposing a candidate generation and re-ranking based framework (CIGAR), which first learns a preference-preserving binary embedding for building a hash table to retrieve candidates, and then learns to re-rank the candidates using real-valued ranking models with a candidate-oriented objective. We perform a comprehensive study on several large-scale real-world datasets consisting of millions of users/items and hundreds of millions of interactions. Our results show that CIGAR significantly boosts the Top-N accuracy against state-of-the-art recommendation models, while reducing the query time by orders of magnitude. We hope that this work could draw more attention to the candidate generation problem in recommender systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑