arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.03318cs.IR
收藏

AIM:点击率预测的自动交互机

AIM: Automatic Interaction Machine for Click-Through Rate Prediction

Chenxu Zhu, Bo Chen, Weinan Zhang, Jincai Lai, Ruiming Tang, Xiuqiang He, Zhenguo Li, Yong Yu

摘要:

特征嵌入学习和特征交互建模是用于点击率(CTR)预测的深度模型的两个关键组成部分。大多数现有的深度CTR模型存在以下三个问题。首先,功能交互要么是手动设计的,要么只是枚举。其次,所有的功能交互建模具有相同的交互功能。第三,在大多数现有模型中,不同的特征共享相同的嵌入大小,这导致内存效率低下。针对上述三个问题,提出了一种基于特征交互搜索、交互函数搜索和嵌入维搜索的自动交互机(AIM),在统一的框架下自动选择重要的特征交互、合适的交互函数和必要的嵌入维。具体而言,FIS组件自动识别不同顺序的基本功能的相互作用与无用的修剪; IFS组件选择适当的交互功能,为每个单独的功能交互在一个可学习的方式; EDS组件自动搜索适当的嵌入大小为每个功能。在三个大规模数据集上的离线实验验证了AIM的优越性能。在一个主流应用市场的推荐服务中进行的为期三周的在线A/B测试显示,AIM在CTR方面将DeepFM模型提高了4.4%。

英文摘要:

Feature embedding learning and feature interaction modeling are two crucial components of deep models for Click-Through Rate (CTR) prediction. Most existing deep CTR models suffer from the following three problems. First, feature interactions are either manually designed or simply enumerated. Second, all the feature interactions are modeled with an identical interaction function. Third, in most existing models, different features share the same embedding size which leads to memory inefficiency. To address these three issues mentioned above, we propose Automatic Interaction Machine (AIM) with three core components, namely, Feature Interaction Search (FIS), Interaction Function Search (IFS) and Embedding Dimension Search (EDS), to select significant feature interactions, appropriate interaction functions and necessary embedding dimensions automatically in a unified framework. Specifically, FIS component automatically identifies different orders of essential feature interactions with useless ones pruned; IFS component selects appropriate interaction functions for each individual feature interaction in a learnable way; EDS component automatically searches proper embedding size for each feature. Offline experiments on three large-scale datasets validate the superior performance of AIM. A three-week online A/B test in the recommendation service of a mainstream app market shows that AIM improves DeepFM model by 4.4% in terms of CTR.

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。

↑