AIM: Automatic Interaction Machine for Click-Through Rate Prediction
This work addresses inefficiencies in CTR prediction for recommendation systems, offering an incremental improvement through automated optimization.
The paper tackles the problems of manual feature interaction design, uniform interaction functions, and fixed embedding sizes in deep CTR prediction models by proposing the Automatic Interaction Machine (AIM), which automatically selects significant interactions, appropriate functions, and embedding dimensions, achieving a 4.4% CTR improvement over DeepFM in an online A/B test.
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.