AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction

TL;DR

AutoFIS is a two-stage algorithm that automatically selects important feature interactions for factorization models in CTR prediction, improving accuracy while reducing computational costs.

Contribution

It introduces a continuous relaxation approach for feature interaction selection, enabling automatic identification and removal of redundant interactions during training.

Findings

AutoFIS significantly improves CTR and CVR in experiments.

It reduces computational costs compared to enumerating all interactions.

Deployed in Huawei App Store, it boosted DeepFM performance by over 20%.

Abstract

Learning feature interactions is crucial for click-through rate (CTR) prediction in recommender systems. In most existing deep learning models, feature interactions are either manually designed or simply enumerated. However, enumerating all feature interactions brings large memory and computation cost. Even worse, useless interactions may introduce noise and complicate the training process. In this work, we propose a two-stage algorithm called Automatic Feature Interaction Selection (AutoFIS). AutoFIS can automatically identify important feature interactions for factorization models with computational cost just equivalent to training the target model to convergence. In the \emph{search stage}, instead of searching over a discrete set of candidate feature interactions, we relax the choices to be continuous by introducing the architecture parameters. By implementing a regularized optimizer over the architecture parameters, the model can automatically identify and remove the redundant feature interactions during the training process of the model. In the \emph{re-train stage}, we keep the architecture parameters serving as an attention unit to further boost the performance. Offline experiments on three large-scale datasets (two public benchmarks, one private) demonstrate that AutoFIS can significantly improve various FM based models. AutoFIS has been deployed onto the training platform of Huawei App Store recommendation service, where a 10-day online A/B test demonstrated that AutoFIS improved the DeepFM model by 20.3\% and 20.1\% in terms of CTR and CVR respectively.