# Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving

arXiv: https://arxiv.org/abs/2109.05236 · HTML: https://mlsanity.com/paper/2109.05236/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2021.

## Built on by (most cited first, 6 of 6)

- [A Survey on Federated Recommendation Systems](https://mlsanity.com/paper/2301.00767/) (2022)
- [FedCL: Federated Contrastive Learning for Privacy-Preserving Recommendation](https://mlsanity.com/paper/2204.09850/) (2022)
- [JobFormer: Skill-Aware Job Recommendation with Semantic-Enhanced Transformer](https://mlsanity.com/paper/2404.04313/) (2024)
- [Robust Quantity-Aware Aggregation for Federated Learning](https://mlsanity.com/paper/2205.10848/) (2022)
- [A Survey on LLM-based News Recommender Systems](https://mlsanity.com/paper/2502.09797/) (2025)
- [Hierarchical Multi-Persona Induction from User Behavioral Logs: Learning Evidence-Grounded and Truthful Personas](https://mlsanity.com/paper/2604.26120/) (2026)

## Abstract (arXiv)

News recommendation is important for personalized online news services. Most existing news recommendation methods rely on centrally stored user behavior data to both train models offline and provide online recommendation services. However, user data is usually highly privacy-sensitive, and centrally storing them may raise privacy concerns and risks. In this paper, we propose a unified news recommendation framework, which can utilize user data locally stored in user clients to train models and serve users in a privacy-preserving way. Following a widely used paradigm in real-world recommender systems, our framework contains two stages. The first one is for candidate news generation (i.e., recall) and the second one is for candidate news ranking (i.e., ranking). At the recall stage, each client locally learns multiple interest representations from clicked news to comprehensively model user interests. These representations are uploaded to the server to recall candidate news from a large news pool, which are further distributed to the user client at the ranking stage for personalized news display. In addition, we propose an interest decomposer-aggregator method with perturbation noise to better protect private user information encoded in user interest representations. Besides, we collaboratively train both recall and ranking models on the data decentralized in a large number of user clients in a privacy-preserving way. Experiments on two real-world news datasets show that our method can outperform baseline methods and effectively protect user privacy.