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.
翻译:嵌入学习的特性和特征互动模型是用于点击浏览率(CTR)预测的深模型的两个关键组成部分。大多数现有的深 CTR 模型存在以下三个问题。首先,特征互动是人工设计或简单列举的。第二,所有特征互动都是以相同的互动功能建模的。第三,在大多数现有模型中,不同的特征具有相同的嵌入大小,导致记忆效率不高。为了解决上述这三个问题,我们提议自动互动机(AIM)具有三个核心组成部分,即功能互动搜索(FIS)、互动功能搜索(IFS)和嵌入尺寸搜索(EDS),以选择重要的特征互动、适当的互动功能和必要的嵌入尺寸搜索(EDS),在统一的框架中自动选择重要的特征互动、适当的互动功能和必要的嵌入维度。具体地说,FIS 组件自动识别基本特征互动的不同顺序,与无效的交互功能;IFSEFS组件为每个单个特征互动选择适当的互动功能,以可学习的方式;EDS组件自动搜索每个特征的适当嵌入大小。在三个大型数据集上的离线实验,以验证AIM的高级性模型/BARTM 服务在深度市场中改进A/4.M 的高级应用软件服务。