English

AIM: Automatic Interaction Machine for Click-Through Rate Prediction

Information Retrieval 2021-12-14 v2

Abstract

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.

Keywords

Cite

@article{arxiv.2111.03318,
  title  = {AIM: Automatic Interaction Machine for Click-Through Rate Prediction},
  author = {Chenxu Zhu and Bo Chen and Weinan Zhang and Jincai Lai and Ruiming Tang and Xiuqiang He and Zhenguo Li and Yong Yu},
  journal= {arXiv preprint arXiv:2111.03318},
  year   = {2021}
}

Comments

Accepted by IEEE Transactions on Knowledge and Data Engineering (TKDE), the codes are availiable at https://github.com/zhuchenxv/AIM. arXiv admin note: text overlap with arXiv:2003.11235

R2 v1 2026-06-24T07:27:20.203Z