# Target-Aware Early Stage Ranking

arXiv: https://arxiv.org/abs/2511.21095 · HTML: https://mlsanity.com/paper/2511.21095/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 26 Nov 2025.

## Builds on (most cited first, 18 of 18)

- [DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems](https://mlsanity.com/paper/2008.13535/) (2020)
- [xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems](https://mlsanity.com/paper/1803.05170/) (2018)
- [Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction](https://mlsanity.com/paper/2006.05639/) (2020)
- [OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment](https://mlsanity.com/paper/2502.18965/) (2025)
- [Behavior Sequence Transformer for E-commerce Recommendation in Alibaba](https://mlsanity.com/paper/1905.06874/) (2019)
- [HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling](https://mlsanity.com/paper/2409.12740/) (2024)
- [PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information](https://mlsanity.com/paper/2302.01115/) (2023)
- [End-to-End User Behavior Retrieval in Click-Through RatePrediction Model](https://mlsanity.com/paper/2108.04468/) (2021)
- [Product-based Neural Networks for User Response Prediction over Multi-field Categorical Data](https://mlsanity.com/paper/1807.00311/) (2018)
- [RankMixer: Scaling Up Ranking Models in Industrial Recommenders](https://mlsanity.com/paper/2507.15551/) (2025)
- [IntTower: the Next Generation of Two-Tower Model for Pre-Ranking System](https://mlsanity.com/paper/2210.09890/) (2022)
- [Beyond Two-Tower Matching: Learning Sparse Retrievable Cross-Interactions for Recommendation](https://mlsanity.com/paper/2311.18213/) (2023)
- [Enhancing CTR Prediction through Sequential Recommendation Pre-training: Introducing the SRP4CTR Framework](https://mlsanity.com/paper/2407.19658/) (2024)
- [SilverTorch: A Unified Model-based System to Democratize Large-Scale Recommendation on GPUs](https://mlsanity.com/paper/2511.14881/) (2025)
- [Request-Only Optimization for Recommendation Systems](https://mlsanity.com/paper/2508.05640/) (2025)
- [HIT Model: A Hierarchical Interaction-Enhanced Two-Tower Model for Pre-Ranking Systems](https://mlsanity.com/paper/2505.19849/) (2025)
- [Equip Pre-ranking with Target Attention by Residual Quantization](https://mlsanity.com/paper/2509.16931/) (2025)
- [A Learnable Fully Interacted Two-Tower Model for Pre-Ranking System](https://mlsanity.com/paper/2509.12948/) (2025)

## Built on by (most cited first, 1 of 1)

- [Memory Layer: Train the In-Model Cache for Recommendation Models](https://mlsanity.com/paper/2607.25110/) (2026)

## Abstract (arXiv)

Early Stage Ranking (ESR) in large-scale recommendation systems is dominated by ''user--item decoupling'' Two Tower architectures, which scale efficiently but cannot capture fine-grained, target-aware user--item interactions directly. We propose Target-Aware Early Stage Ranking (TESR), which augments the Two Tower with a Mixture of Attention (MoA) module trained as a request-level sequence modeling over user history. MoA combines (i) Hard Matching Attention (HMA) to capture explicit categorical-ID level overlap signals between user history and candidate item, (ii) target-aware HSTU attention for implicit affinities conditioned on the candidate, and (iii) target dependent and independent cross-attention for symmetric user-item contextualization. On top of this, a Multi-Logit Parameterized Gating (MLPG) head amplifies these signals at scoring time. To keep latency within ESR budgets, we co-design the architecture with FP8 quantization, custom kernels, and a Torch Inductor compilation path. On a production deployment, TESR delivers consistent offline NE wins and online topline gains, and is, to our knowledge, the first deployment of full target-aware attention sequence modeling in an ESR stage at this scale.