# HIT Model: A Hierarchical Interaction-Enhanced Two-Tower Model for Pre-Ranking Systems

arXiv: https://arxiv.org/abs/2505.19849 · HTML: https://mlsanity.com/paper/2505.19849/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2025.

## Built on by (most cited first, 2 of 2)

- [Target-Aware Early Stage Ranking](https://mlsanity.com/paper/2511.21095/) (2025)
- [Connected Content Retriever: Dense Graph Edge Features Powering Pre-Ranking at LinkedIn](https://mlsanity.com/paper/2609.22441/) (2026)

## Abstract (arXiv)

Online display advertising platforms rely on pre-ranking systems to efficiently filter and prioritize candidate ads from large corpora, balancing relevance to users with strict computational constraints. The prevailing two-tower architecture, though highly efficient due to its decoupled design and pre-caching, suffers from cross-domain interaction and coarse similarity metrics, undermining its capacity to model complex user-ad relationships. In this study, we propose the Hierarchical Interaction-Enhanced Two-Tower (HIT) model, a new architecture that augments the two-tower paradigm with two key components: textitgenerators that pre-generate holistic vectors incorporating coarse-grained user-ad interactions through a dual-generator framework with a cosine-similarity-based generation loss as the training objective, and textitmulti-head representers that project embeddings into multiple latent subspaces to capture fine-grained, multi-faceted user interests and multi-dimensional ad attributes. This design enhances modeling effectiveness without compromising inference efficiency. Extensive experiments on public datasets and large-scale online A/B testing on Tencent's advertising platform demonstrate that HIT significantly outperforms several baselines in relevance metrics, yielding a 1.66% increase in Gross Merchandise Volume and a 1.55% improvement in Return on Investment, alongside similar serving latency to the vanilla two-tower models. The HIT model has been successfully deployed in Tencent's online display advertising system, serving billions of impressions daily. The code is available at https://github.com/HarveyYang123/HITmodel.