Feature-level Deeper Self-Attention Network for Sequential Recommendation-猫眼课题宝

DOI：

10.24963/ijcai.2019/600

发表时间：

2019-08

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Tingting Zhang;Pengpeng Zhao;Yanchi Liu;Victor S. Sheng;Jiajie Xu;Deqing Wang;Guanfeng Liu;Xiaofang Zhou

顺序推荐是一种旨在推荐用户在不久的将来可能会交互的下一个项目的方法，在各种互联网应用中已经成为必不可少的。现有的方法通常考虑项目之间的过渡模式，但忽略了项目的特征之间的过渡模式。我们认为，只有项目级序列不能揭示完整的序列模式，而显式和隐式的特征级序列可以帮助提取完整的序列模式。在本文中，我们提出了一种新的方法命名为层次更深的自我注意力网络（FDSA）的顺序推荐。具体来说，FDSA首先通过香草机制将项目的各种异构特征集成到具有不同权重的特征序列中。然后，FDSA分别在项目级序列和特征级序列上应用分离的自注意块，对项目转移模式和特征转移模式进行建模。然后，我们将这两个块的输出整合到一个完全连接的层，用于下一个项目推荐。最后，综合实验结果表明，考虑特征之间的过渡关系，可以显着提高顺序推荐的性能。

Sequential recommendation, which aims to recommend next item that the user will likely interact in a near future, has become essential in various Internet applications. Existing methods usually consider the transition patterns between items, but ignore the transition patterns between features of items. We argue that only the item-level sequences cannot reveal the full sequential patterns, while explicit and implicit feature-level sequences can help extract the full sequential patterns. In this paper, we propose a novel method named Feature-level Deeper Self-Attention Network (FDSA) for sequential recommendation. Specifically, FDSA first integrates various heterogeneous features of items into feature sequences with different weights through a vanilla mechanism. After that, FDSA applies separated self-attention blocks on item-level sequences and feature-level sequences, respectively, to model item transition patterns and feature transition patterns. Then, we integrate the outputs of these two blocks to a fully-connected layer for next item recommendation. Finally, comprehensive experimental results demonstrate that considering the transition relationships between features can significantly improve the performance of sequential recommendation.

Feature-level Deeper Self-Attention Network for Sequential Recommendation

文献摘要

被引文献

相似文献