Memorize, Factorize, or be Na\"ive: Learning Optimal Feature Interaction Methods for CTR Prediction
Fuyuan Lyu, Xing Tang, Huifeng Guo, Ruiming Tang, Xiuqiang He, Rui, Zhang, Xue Liu

TL;DR
This paper introduces OptInter, a flexible framework that automatically selects the best feature interaction modeling method for CTR prediction, significantly improving performance and reducing parameters compared to existing approaches.
Contribution
The paper proposes a general framework called OptInter that automatically finds the optimal feature interaction modeling method for each interaction, unifying and enhancing existing deep CTR models.
Findings
OptInter improves state-of-the-art models by up to 2.21%.
It reduces parameters by up to 91% compared to memorized methods.
Extensive experiments validate the effectiveness of OptInter.
Abstract
Click-through rate prediction is one of the core tasks in commercial recommender systems. It aims to predict the probability of a user clicking a particular item given user and item features. As feature interactions bring in non-linearity, they are widely adopted to improve the performance of CTR prediction models. Therefore, effectively modelling feature interactions has attracted much attention in both the research and industry field. The current approaches can generally be categorized into three classes: (1) na\"ive methods, which do not model feature interactions and only use original features; (2) memorized methods, which memorize feature interactions by explicitly viewing them as new features and assigning trainable embeddings; (3) factorized methods, which learn latent vectors for original features and implicitly model feature interactions through factorization functions. Studies…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRecommender Systems and Techniques · Image Retrieval and Classification Techniques · Sentiment Analysis and Opinion Mining
