arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2402.02718cs.IRcs.AI
收藏

面向推荐的时间周期建模去噪

Denoising Time Cycle Modeling for Recommendation

Ant Group(蚂蚁集团)

Sicong Xie, Qunwei Li, Weidi Xu, Kaiming Shen, Shaohu Chen, Wenliang Zhong

AI总结:

本文提出DiCycle方法,通过去噪用户行为并选择与目标物品高度相关的子集,显式建模多样化时间周期模式,在公共和真实数据集上超越现有推荐方法。

摘要:

近年来,对用户-物品交互的时间模式进行建模在推荐系统中引起了广泛关注。我们认为,现有方法忽略了用户行为时间模式的多样性。我们将与目标物品无关的用户行为子集定义为噪声,这些噪声限制了与目标相关的时间周期建模的性能,并影响推荐性能。在本文中,我们提出了去噪时间周期建模(DiCycle),一种新颖的方法,用于对用户行为进行去噪,并选择与目标物品高度相关的用户行为子集。DiCycle能够显式地建模多样化的时间周期模式以用于推荐。我们在公共基准和真实世界数据集上进行了大量实验,证明了DiCycle相对于最先进的推荐方法的优越性能。

英文摘要:

Recently, modeling temporal patterns of user-item interactions have attracted much attention in recommender systems. We argue that existing methods ignore the variety of temporal patterns of user behaviors. We define the subset of user behaviors that are irrelevant to the target item as noises, which limits the performance of target-related time cycle modeling and affect the recommendation performance. In this paper, we propose Denoising Time Cycle Modeling (DiCycle), a novel approach to denoise user behaviors and select the subset of user behaviors that are highly related to the target item. DiCycle is able to explicitly model diverse time cycle patterns for recommendation. Extensive experiments are conducted on both public benchmarks and a real-world dataset, demonstrating the superior performance of DiCycle over the state-of-the-art recommendation methods.

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。

↑