Input features play a crucial role in DNN-based recommender systems with thousands of categorical and continuous fields from users, items, contexts, and interactions. Noisy features and inappropriate embedding dimension assignments can deteriorate the performance of recommender systems and introduce unnecessary complexity in model training and online serving. Optimizing the input configuration of DNN models, including feature selection and embedding dimension assignment, has become one of the essential topics in feature engineering. However, in existing industrial practices, feature selection and dimension search are optimized sequentially, i.e., feature selection is performed first, followed by dimension search to determine the optimal dimension size for each selected feature. Such a sequential optimization mechanism increases training costs and risks generating suboptimal input configurations. To address this problem, we propose a differentiable neural input razor (i-Razor) that enables joint optimization of feature selection and dimension search. Concretely, we introduce an end-to-end differentiable model to learn the relative importance of different embedding regions of each feature. Furthermore, a flexible pruning algorithm is proposed to achieve feature filtering and dimension derivation simultaneously. Extensive experiments on two large-scale public datasets in the Click-Through-Rate (CTR) prediction task demonstrate the efficacy and superiority of i-Razor in balancing model complexity and performance.

翻译：输入特征在基于深度神经网络（DNN）的推荐系统中至关重要，涉及来自用户、物品、上下文及交互的数千个类别型和连续型字段。噪声特征与不恰当的嵌入维度分配会降低推荐系统性能，并增加模型训练与在线服务的复杂性。优化DNN模型的输入配置（包括特征选择与嵌入维度分配）已成为特征工程的核心议题之一。然而，现有工业实践中特征选择与维度搜索采用顺序优化机制——即先执行特征选择，再通过维度搜索确定每个选中特征的最优嵌入维度。这种顺序优化机制不仅增加了训练成本，还可能导致次优的输入配置。为解决该问题，我们提出可微分神经输入剃刀（i-Razor），实现特征选择与维度搜索的联合优化。具体而言，我们引入端到端可微分模型以学习各特征不同嵌入区域的相对重要性，进一步提出灵活的剪枝算法，同步完成特征过滤与维度推导。在点击率（CTR）预测任务的两个大规模公开数据集上的大量实验证明，i-Razor在平衡模型复杂度与性能方面具有有效性与优越性。