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 2311.04590cs.IR
收藏

开放世界假设下的跨域序列推荐再思考

Rethinking Cross-Domain Sequential Recommendation under Open-World Assumptions

Wujiang Xu, Qitian Wu, Runzhong Wang, Mingming Ha, Qiongxu Ma, Linxun Chen, Bing Han, Junchi Yan

AI总结:

针对现有跨域序列推荐方法基于封闭世界假设、在真实开放环境中因分布偏移性能下降的问题,提出含多兴趣信息模块与双重鲁棒估计器的AMID框架,可适配开放环境并提升骨干模型性能,且理论上优于传统IPS估计器。

摘要:

跨域序列推荐(Cross-Domain Sequential Recommendation, CDSR)方法旨在解决单域序列推荐(Single-Domain Sequential Recommendation, SDSR)中存在的数据稀疏与冷启动问题。现有CDSR研究依赖重叠用户设计精细结构以传播跨域信息,但当前方法均基于封闭世界假设,即假定多域间用户完全重叠,且训练环境到测试环境的数据分布保持不变。因此,受数据分布偏移影响,这类方法在在线真实平台上的性能通常较低。为应对开放世界假设下的上述挑战,我们设计了面向跨域序列推荐的自适应多兴趣去偏框架(Adaptive Multi-Interest Debiasing framework, AMID),该框架由多兴趣信息模块(Multi-Interest Information Module, MIM)和双重鲁棒估计器(Doubly Robust Estimator, DRE)组成。我们的框架可自适应开放世界环境,能够提升多数现成单域序列骨干模型用于CDSR时的性能。MIM构建了同时兼顾重叠与非重叠用户的兴趣群组,可有效挖掘用户意图与显式兴趣。为缓解多域间的偏差,我们为CDSR方法开发了DRE。我们还提供了理论分析,证明与以往工作使用的IPS估计器相比,本文提出的估计器在偏差和尾界方面更具优势。

英文摘要:

Cross-Domain Sequential Recommendation (CDSR) methods aim to tackle the data sparsity and cold-start problems present in Single-Domain Sequential Recommendation (SDSR). Existing CDSR works design their elaborate structures relying on overlapping users to propagate the cross-domain information. However, current CDSR methods make closed-world assumptions, assuming fully overlapping users across multiple domains and that the data distribution remains unchanged from the training environment to the test environment. As a result, these methods typically result in lower performance on online real-world platforms due to the data distribution shifts. To address these challenges under open-world assumptions, we design an \textbf{A}daptive \textbf{M}ulti-\textbf{I}nterest \textbf{D}ebiasing framework for cross-domain sequential recommendation (\textbf{AMID}), which consists of a multi-interest information module (\textbf{MIM}) and a doubly robust estimator (\textbf{DRE}). Our framework is adaptive for open-world environments and can improve the model of most off-the-shelf single-domain sequential backbone models for CDSR. Our MIM establishes interest groups that consider both overlapping and non-overlapping users, allowing us to effectively explore user intent and explicit interest. To alleviate biases across multiple domains, we developed the DRE for the CDSR methods. We also provide a theoretical analysis that demonstrates the superiority of our proposed estimator in terms of bias and tail bound, compared to the IPS estimator used in previous work.

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。

↑