A Learnable Fully Interacted Two-Tower Model for Pre-Ranking System
Authors:
- Chao XiongCXChao Xiong
- Xianwen YuXYXianwen Yu
- Wei XuWXWei Xu
- Lei ChengLCLei Cheng
- Chuan YuanCYChuan Yuan
- Linjian MoLMLinjian Mo
Preprint
Abstract
Pre-ranking plays a crucial role in large-scale recommender systems by significantly improving the efficiency and scalability within the constraints of providing high-quality candidate sets in real time. The two-tower model is widely used in pre-ranking systems due to a good balance between efficiency and effectiveness with decoupled architecture, which independently processes user and item inputs before calculating their interaction (e.g. dot product or similarity measure). However, this independence also leads to the lack of information interaction between the two towers, resulting in less effectiveness. In this paper, a novel architecture named learnable Fully Interacted Two-tower Model (FIT) is proposed, which enables rich information interactions while ensuring inference efficiency. FIT mainly consists of two parts: Meta Query Module (MQM) and Lightweight Similarity Scorer (LSS). Specifically, MQM introduces a learnable item meta matrix to achieve expressive early interaction between user and item features. Moreover, LSS is designed to further obtain effective late interaction between the user and item towers. Finally, experimental results on several public datasets show that our proposed FIT significantly outperforms the state-of-the-art baseline pre-ranking models.Keywords
All Related Versions
- Version 1, 2025-09-16, ArXiv
- Published version: , 2182.
This publication has 3 references indexed in Scilit:
- Product-Based Neural Networks for User Response Prediction over Multi-Field Categorical DataACM Transactions on Information Systems, 2018
- DeepFM: A Factorization-Machine based Neural Network for CTR Prediction2017
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015