IntTower: the Next Generation of Two-Tower Model for Pre-Ranking System
Xiangyang Li, Bo Chen, HuiFeng Guo, Jingjie Li, Chenxu Zhu, Xiang, Long, Sujian Li, Yichao Wang, Wei Guo, Longxia Mao, Jinxing Liu, Zhenhua, Dong, Ruiming Tang

TL;DR
IntTower introduces an advanced two-tower model that enhances interaction modeling between user and item features while maintaining high inference efficiency, significantly improving pre-ranking accuracy in industrial systems.
Contribution
The paper proposes IntTower, a novel two-tower model with modules for explicit and implicit feature interactions, balancing accuracy and efficiency in pre-ranking systems.
Findings
Outperforms state-of-the-art pre-ranking models on public datasets.
Achieves comparable performance to ranking models.
Proven effective in large-scale advertisement pre-ranking system.
Abstract
Scoring a large number of candidates precisely in several milliseconds is vital for industrial pre-ranking systems. Existing pre-ranking systems primarily adopt the \textbf{two-tower} model since the ``user-item decoupling architecture'' paradigm is able to balance the \textit{efficiency} and \textit{effectiveness}. However, the cost of high efficiency is the neglect of the potential information interaction between user and item towers, hindering the prediction accuracy critically. In this paper, we show it is possible to design a two-tower model that emphasizes both information interactions and inference efficiency. The proposed model, IntTower (short for \textit{Interaction enhanced Two-Tower}), consists of Light-SE, FE-Block and CIR modules. Specifically, lightweight Light-SE module is used to identify the importance of different features and obtain refined feature representations in…
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
TopicsAdvanced Text Analysis Techniques · Sentiment Analysis and Opinion Mining · Complex Network Analysis Techniques
