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

TL;DR

Uni-FedRec introduces a privacy-preserving news recommendation framework that trains models locally on user devices, protecting user data while maintaining high recommendation quality through decentralized learning.

Contribution

The paper presents a novel unified framework for privacy-preserving news recommendation that combines local user data training with decentralized model training and interest representation perturbation.

Findings

Outperforms baseline methods on real-world datasets

Effectively protects user privacy with interest perturbation

Maintains recommendation accuracy comparable to centralized models

Abstract

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.