Relation‐Level User Behavior Modeling for Click‐Through Rate Prediction
Relation‐Level User Behavior Modeling for Click‐Through Rate Prediction
复制标题
DOI：
10.1002/tee.23522
复制
发表时间：
2021-11
影响因子：
1
通讯作者：
Hangyu Deng;Yanling Tian;Jia Luo;Jinglu Hu
中科院分区：
文献类型：
--
作者：
Hangyu Deng;Yanling Tian;Jia Luo;Jinglu Hu
许多最近基于用户行为的点进率模型采用类似的项级范例：通过序列模型和/或汇集机制从项表示列表中学习用户表示。然而，序列模型通常对行为序列的确切顺序很敏感，而项目级别的汇集机制只是忽略了按时间顺序的信息。在本文中，我们通过将长项目序列分解成一组极短的序列(项目对)并对它们进行关系推理来平衡这两种方法。更具体地说，关系推理机制由两部分组成，旨在捕获行为序列中的各种过渡模式。采用关注汇聚层来强调那些与目标项高度相关的关系级信号。因此，我们的方法基本上是前两种方法之间的中间地带。为了验证该方法的有效性，我们在三个公共数据集上进行了广泛的实验。实验结果表明，我们的方法取得了比其他方法更好的性能。此外，我们还探索了模型的性质，并通过控制实验验证了各组成部分的有效性。©2021日本电气工程师学会。由威利期刊有限责任公司出版。
Many recent user behavior based click‐through rate models adopt a similar item‐level paradigm: learn the user representation from a list of item representations via a sequence model and/or a pooling mechanism. However, sequence models are usually sensitive to the exact order of the behavior sequence, while item‐level pooling mechanisms simply neglect the chronological information. In this paper, we balance the two approaches by decomposing the long item sequence into a group of extremely short sequences (item pairs) and conducting relational reasoning on them. More specifically, the relational reasoning mechanism consists of two parts, which are designed for capturing various transitional patterns in the behavior sequences. An attentive pooling layer is employed to emphasize those relation‐level signals that are highly related to the target item. Therefore, our approach is essentially a middle ground between the previous two approaches. To verify the effectiveness of our method, we conduct extensive experiments on three public datasets. Experimental results show that our methods achieve better performance than others. Besides, we explore the properties of our model and verify the effectiveness of each component by controlled experiments. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.