arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.04553cs.IRcs.AI
收藏

迟做总比不做好:推荐编辑的形式化与基准评测

Better Late Than Never: Formulating and Benchmarking Recommendation Editing

Zhejiang University(浙江大学);Texas A&M University(得克萨斯农工大学);New York University Shanghai(纽约大学上海分校)

Chengyu Lai, Sheng Zhou, Zhimeng Jiang, Qiaoyu Tan, Yuanchen Bei, Jiawei Chen, Ningyu Zhang, Jiajun Bu

AI总结:

本文形式化提出推荐编辑任务,在不访问训练数据或重训模型的前提下纠正已知不合适推荐,并给出目标、指标及基于 Editing BPR Loss 的综合基准。

摘要:

推荐系统在根据用户偏好向其推荐物品方面发挥着关键作用。然而,在在线平台中,由于模型容量有限、数据质量较差或用户兴趣不断变化,这些系统不可避免地会提供不合适的推荐。为提升用户体验,必须高效纠正此类不合适的推荐行为。本文引入了一项新颖且重要的任务,称为推荐编辑,其重点是修改已知且不合适的推荐行为。具体而言,该任务旨在调整推荐模型,以在不访问训练数据或不重新训练模型的情况下消除已知的不合适物品。我们正式定义了推荐编辑问题,并提出三个主要目标:严格纠正、协同纠正和集中纠正。我们设计了三个评估指标,以定量评估每个目标的达成情况。我们使用新颖的 Editing Bayesian Personalized Ranking Loss,提出了一个简单而有效的推荐编辑基准。为证明所提方法的有效性,我们建立了一个综合基准,纳入了来自相关领域的多种方法。代码库可在 https://github.com/cycl2018/Recommendation-Editing 获取。

英文摘要:

Recommendation systems play a pivotal role in suggesting items to users based on their preferences. However, in online platforms, these systems inevitably offer unsuitable recommendations due to limited model capacity, poor data quality, or evolving user interests. Enhancing user experience necessitates efficiently rectify such unsuitable recommendation behaviors. This paper introduces a novel and significant task termed recommendation editing, which focuses on modifying known and unsuitable recommendation behaviors. Specifically, this task aims to adjust the recommendation model to eliminate known unsuitable items without accessing training data or retraining the model. We formally define the problem of recommendation editing with three primary objectives: strict rectification, collaborative rectification, and concentrated rectification. Three evaluation metrics are developed to quantitatively assess the achievement of each objective. We present a straightforward yet effective benchmark for recommendation editing using novel Editing Bayesian Personalized Ranking Loss. To demonstrate the effectiveness of the proposed method, we establish a comprehensive benchmark that incorporates various methods from related fields. Codebase is available at https://github.com/cycl2018/Recommendation-Editing.

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。

↑