Position-aware context attention for session-based recommendation
Position-aware context attention for session-based recommendation
复制标题
基于会话的推荐的位置感知上下文关注
DOI：
10.1016/j.neucom.2019.09.016
复制
发表时间：
2020-02-01
期刊：
影响因子：
6
通讯作者：
Xu, Congfu
中科院分区：
文献类型：
--
作者：
Cao, Yi;Zhang, Weifeng;Xu, Congfu
在基于会话的推荐场景中，用户配置文件不可用，预测他们的行为是一个具有挑战性的问题。以前解决这个问题的主要方法是基于RNN的模型。最近，允许更高并行化的注意力机制在这个问题上显示出显着的改进。然而，现有的基于注意力的方法中没有一个明确地利用序列中的位置信息和上下文信息。我们假设，一个项目通常表现出不同的重要性水平时，它出现在不同的位置在一个序列。为此，提出了一种位置感知上下文注意力（PACA）模型，该模型综合考虑了项目的位置信息和上下文信息，提高了推荐性能. PACA引入位置向量来对位置信息进行建模，并利用池化函数来生成上下文特征向量。然后将这两个向量结合起来，生成会话中每个项目的注意力权重。为了进一步提高性能，我们使用多头方法将多个并行注意力模块联合收割机。在两个真实世界数据集上的实验表明，与现有的方法相比，所提出的注意力模型能够实现非常有前途的性能。最后，我们将位置向量可视化，以明确分析序列中每个位置的重要性。(C)2019 Elsevier B.V.版权所有。
In session-based recommendation scenarios where user profiles are not available, predicting their behaviors is a challenging problem. Previous dominant methods to solve this problem are RNN-based models. Recently, attention mechanisms that allow higher parallelization have shown significant improvement on this issue. However, none of the existing attention-based methods explicitly takes advantage of both the position information and context information in a sequence. We assume that one item usually exhibits different levels of importance when it appears in different positions in a sequence. Therefore, a position-aware context attention (PACA) model is proposed as a remedy, which improves the recommendation performance by taking into account both the position information and the context information of items. PACA introduces positional vectors to model the position information and utilizes a pooling function to generate the context feature vectors. Then the two vectors are combined to generate the attention weight for each item in a session. To further improve the performance, we use a multi-head method to combine several parallel attention modules. Extensive experiments on two real-world datasets show that the proposed attention model is able to achieve very promising performance in comparison with the state-of-the-art methods. Finally, we visualize the positional vectors to explicitly analyze the importance of each position in a sequence. (C) 2019 Elsevier B.V. All rights reserved.