# Empowering Long-tail Item Recommendation through Cross Decoupling Network (CDN)

arXiv: https://arxiv.org/abs/2210.14309 · HTML: https://mlsanity.com/paper/2210.14309/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2022.

## Built on by (most cited first, 12 of 12)

- [CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation](https://mlsanity.com/paper/2403.06447/) (2024)
- [Unifying Generative and Dense Retrieval for Sequential Recommendation](https://mlsanity.com/paper/2411.18814/) (2024)
- [Simple-Sampling and Hard-Mixup with Prototypes to Rebalance Contrastive Learning for Text Classification](https://mlsanity.com/paper/2405.11524/) (2024)
- [A Hybrid Cross-Stage Coordination Pre-ranking Model for Online Recommendation Systems](https://mlsanity.com/paper/2502.10284/) (2025)
- [BehaveGPT: A Foundation Model for Large-scale User Behavior Modeling](https://mlsanity.com/paper/2505.17631/) (2025)
- [LLM-empowered Dynamic Prompt Routing for Vision-Language Models Tuning under Long-Tailed Distributions](https://mlsanity.com/paper/2508.15688/) (2025)
- [Sequential Recommendation with Controllable Diversification: Representation Degeneration and Diversity](https://mlsanity.com/paper/2306.11986/) (2023)
- [Prompt Tuning for Item Cold-start Recommendation](https://mlsanity.com/paper/2412.18082/) (2024)
- [Creator-Side Recommender System: Challenges, Designs, and Applications](https://mlsanity.com/paper/2502.20497/) (2025)
- [Taming the Long Tail: Efficient Item-wise Sharpness-Aware Minimization for LLM-based Recommender Systems](https://mlsanity.com/paper/2603.12752/) (2026)
- [Debiasing Message Passing to Mitigate Popularity Bias in GNN-based Collaborative Filtering](https://mlsanity.com/paper/2605.11145/) (2026)
- [Denoising Implicit Feedback for Cold-start Recommendation](https://mlsanity.com/paper/2606.19658/) (2026)

## Abstract (arXiv)

Industry recommender systems usually suffer from highly-skewed long-tail item distributions where a small fraction of the items receives most of the user feedback. This skew hurts recommender quality especially for the item slices without much user feedback. While there have been many research advances made in academia, deploying these methods in production is very difficult and very few improvements have been made in industry. One challenge is that these methods often hurt overall performance; additionally, they could be complex and expensive to train and serve. In this work, we aim to improve tail item recommendations while maintaining the overall performance with less training and serving cost. We first find that the predictions of user preferences are biased under long-tail distributions. The bias comes from the differences between training and serving data in two perspectives: 1) the item distributions, and 2) user's preference given an item. Most existing methods mainly attempt to reduce the bias from the item distribution perspective, ignoring the discrepancy from user preference given an item. This leads to a severe forgetting issue and results in sub-optimal performance. To address the problem, we design a novel Cross Decoupling Network (CDN) (i) decouples the learning process of memorization and generalization on the item side through a mixture-of-expert architecture; (ii) decouples the user samples from different distributions through a regularized bilateral branch network. Finally, a new adapter is introduced to aggregate the decoupled vectors, and softly shift the training attention to tail items. Extensive experimental results show that CDN significantly outperforms state-of-the-art approaches on benchmark datasets. We also demonstrate its effectiveness by a case study of CDN in a large-scale recommendation system at Google.