# Hierarchical Group-wise Ranking Framework for Recommendation Models

arXiv: https://arxiv.org/abs/2506.12756 · HTML: https://mlsanity.com/paper/2506.12756/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 15 Jun 2025.

## Builds on (most cited first, 10 of 10)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Not All Samples Are Created Equal: Deep Learning with Importance Sampling](https://mlsanity.com/paper/1803.00942/) (2018)
- [Joint Optimization of Ranking and Calibration with Contextualized Hybrid Model](https://mlsanity.com/paper/2208.06164/) (2022)
- [Regression Compatible Listwise Objectives for Calibrated Ranking with Binary Relevance](https://mlsanity.com/paper/2211.01494/) (2022)
- [Real-time Indexing for Large-scale Recommendation by Streaming Vector Quantization Retriever](https://mlsanity.com/paper/2501.08695/) (2025)
- [Understanding the Ranking Loss for Recommendation with Sparse User Feedback](https://mlsanity.com/paper/2403.14144/) (2024)
- [A Self-boosted Framework for Calibrated Ranking](https://mlsanity.com/paper/2406.08010/) (2024)

## Abstract (arXiv)

In modern recommender systems, CTR/CVR models are increasingly trained with ranking objectives to improve item ranking quality. While this shift aligns training more closely with serving goals, most existing methods rely on in-batch negative sampling, which predominantly surfaces easy negatives. This limits the model's ability to capture fine-grained user preferences and weakens overall ranking performance. To address this, we propose a Hierarchical Group-wise Ranking Framework with two key components. First, we apply residual vector quantization to user embeddings to generate hierarchical user codes that partition users into hierarchical, trie-structured clusters. Second, we apply listwise ranking losses to user-item pairs at each level of the hierarchy, where shallow levels group loosely similar users and deeper levels group highly similar users, reinforcing learning-to-rank signals through progressively harder negatives. Since users with similar preferences and content exposure tend to yield more informative negatives, applying ranking losses within these hierarchical user groups serves as an effective approximation of hard negative mining. Our approach improves ranking performance without requiring complex real-time context collection or retrieval infrastructure. Extensive experiments demonstrate that the proposed framework consistently enhances both model calibration and ranking accuracy, offering a scalable and practical solution for industrial recommender systems.