[论文解读] Denoising User-aware Memory Network for Recommendation

Zhi Bian, Shaojun Zhou+7 more|arXiv (Cornell University)|Jul 12, 2021

Recommender Systems and Techniques参考文献 45被引用 4

一句话总结

该论文提出DUMN，一种去噪用户感知记忆网络，通过正交映射利用显式反馈净化噪声隐式反馈，借助改进的记忆网络建模长期用户偏好，并通过门控机制融合短期与长期兴趣，从而提升点击率（CTR）预测性能。DUMN在两个真实世界电商数据集上达到最先进性能，展现出在捕捉无偏用户偏好方面更高的准确性和鲁棒性。

ABSTRACT

For better user satisfaction and business effectiveness, more and more attention has been paid to the sequence-based recommendation system, which is used to infer the evolution of users' dynamic preferences, and recent studies have noticed that the evolution of users' preferences can be better understood from the implicit and explicit feedback sequences. However, most of the existing recommendation techniques do not consider the noise contained in implicit feedback, which will lead to the biased representation of user interest and a suboptimal recommendation performance. Meanwhile, the existing methods utilize item sequence for capturing the evolution of user interest. The performance of these methods is limited by the length of the sequence, and can not effectively model the long-term interest in a long period of time. Based on this observation, we propose a novel CTR model named denoising user-aware memory network (DUMN). Specifically, the framework: (i) proposes a feature purification module based on orthogonal mapping, which use the representation of explicit feedback to purify the representation of implicit feedback, and effectively denoise the implicit feedback; (ii) designs a user memory network to model the long-term interests in a fine-grained way by improving the memory network, which is ignored by the existing methods; and (iii) develops a preference-aware interactive representation component to fuse the long-term and short-term interests of users based on gating to understand the evolution of unbiased preferences of users. Extensive experiments on two real e-commerce user behavior datasets show that DUMN has a significant improvement over the state-of-the-art baselines. The code of DUMN model has been uploaded as an additional material.

研究动机与目标

• 解决隐式反馈中的噪声问题，该问题会扭曲用户偏好表征并降低推荐性能。
• 更有效地建模长期用户兴趣，克服基于RNN的序列长度依赖方法的局限性。
• 通过偏好感知方式融合短期与长期兴趣，提升CTR预测的准确性。
• 构建一个统一框架，同时利用隐式反馈（点击/未点击）与显式反馈（点赞/不喜欢），实现无偏偏好建模。
• 在真实推荐场景中验证特征净化与细粒度长期兴趣表征的有效性。

提出的方法

• 引入特征净化（FP）模块，利用正交映射基于显式反馈对齐并优化隐式反馈表征，降低噪声。
• 提出用户记忆网络（UMN），增强记忆容量与稳定性，以捕捉长期用户兴趣。
• 设计偏好感知交互表征（PAIR）模块，通过门控机制动态融合短期与长期兴趣。
• 构建四类反馈序列——点击、未点击、点赞与不喜欢，实现全面的用户偏好建模。
• 采用去噪策略，利用显式反馈更高的可靠性来校正噪声隐式反馈表征。
• 采用多任务学习目标端到端训练模型，联合优化CTR预测与不喜欢预测。

实验结果

研究问题

• RQ1 能否有效利用显式反馈对隐式反馈表征进行去噪，从而改善用户偏好建模？
• RQ2 相较于标准RNN，改进的记忆网络架构是否能更好地捕捉并保持长期用户兴趣？
• RQ3 通过门控机制融合短期与长期兴趣，是否能带来更准确且稳定的CTR预测？
• RQ4 在真实世界电商推荐任务中，所提出的DUMN模型相较于最先进基线模型表现如何？
• RQ5 模型在捕捉用户不感兴趣（如不喜欢预测）方面改善程度如何，是否能降低用户挫败感？

主要发现

• DUMN在两个真实电商数据集上显著优于最先进基线模型，展现出卓越的CTR预测性能。
• 特征净化模块有效降低了隐式反馈中的噪声，可视化结果表明净化后的点击/未点击表征与显式点赞/不喜欢表征之间的分离度明显提升。
• 用户记忆网络成功捕捉到稳定的长期用户兴趣，同一用户在嵌入空间中的表征随时间聚类在一起。
• 短期兴趣表征分布更分散，而长期表征则收敛至稳定且紧凑的区域，证实模型具备区分短暂偏好与持久偏好的能力。
• DUMN在不喜欢预测任务上优于DFN基线模型，表明其对用户不感兴趣更敏感，模型鲁棒性更强。
• 可视化结果证实，FP与UMN模块有效提升了模型学习无偏、细粒度用户偏好的能力。