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 2201.05333cs.IR
收藏

注意力胜过自我注意力:基于动态Transformer编码器的意图感知重排序

Attention over Self-attention:Intention-aware Re-ranking with Dynamic Transformer Encoders for Recommendation

Zhuoyi Lin, Sheng Zang, Rundong Wang, Zhu Sun, J. Senthilnath, Chi Xu, Chee-Keong Kwoh

摘要:

重新排序模型细化了由先前的全局排序模型生成的项目推荐列表,这已经证明了它们在提高推荐质量方面的有效性。然而,大多数现有的重排序解决方案只学习隐式反馈与共享的预测模型,这令人遗憾地忽略了不同的用户意图下的项目间的关系。在本文中,我们提出了一种新的意图感知重排序模型与动态Transformer编码器(RAISE),旨在执行用户特定的预测,为每个单独的用户的基础上,她的意图。具体来说,我们首先提出挖掘潜在的用户意图从文本评论与意图发现模块(IDM)。通过区分评论信息的重要性与共同注意力网络,潜在的用户意图可以显式地建模为每个用户项目对。然后,我们引入了一个动态的Transformer编码器(DTE),以捕捉用户特定的项目之间的项目候选人无缝地容纳通过IDM学习潜在的用户意图之间的关系。因此,人们不仅可以实现更个性化的推荐,而且还可以通过在现有的推荐引擎上构建RAISE来获得相应的解释。在4个公开数据集上的实验结果表明,本文提出的RAISE算法在Precision@5、MAP@5和NDCG@5下的相对性能分别提高了13.95%、9.60%和13.03%。

英文摘要:

Re-ranking models refine item recommendation lists generated by the prior global ranking model, which have demonstrated their effectiveness in improving the recommendation quality. However, most existing re-ranking solutions only learn from implicit feedback with a shared prediction model, which regrettably ignore inter-item relationships under diverse user intentions. In this paper, we propose a novel Intention-aware Re-ranking Model with Dynamic Transformer Encoder (RAISE), aiming to perform user-specific prediction for each individual user based on her intentions. Specifically, we first propose to mine latent user intentions from text reviews with an intention discovering module (IDM). By differentiating the importance of review information with a co-attention network, the latent user intention can be explicitly modeled for each user-item pair. We then introduce a dynamic transformer encoder (DTE) to capture user-specific inter-item relationships among item candidates by seamlessly accommodating the learned latent user intentions via IDM. As such, one can not only achieve more personalized recommendations but also obtain corresponding explanations by constructing RAISE upon existing recommendation engines. Empirical study on four public datasets shows the superiority of our proposed RAISE, with up to 13.95%, 9.60%, and 13.03% relative improvements evaluated by Precision@5, MAP@5, and NDCG@5 respectively.

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。

↑