Communication Dans Un Congrès Année : 2025

PriviRec: Confidential and Decentralized Graph Filtering for Recommender Systems

Résumé

Recent advances in recommender systems have shown that relying on graph filters, such as the normalized item-item adjacency matrix and the ideal low-pass filter yields competitive performance and scales better than Graph Convolutional Networks-based solutions. However, these solutions require centralizing user data, which raises concerns over data privacy, security, and the monopolization of user data by a few actors. To address those concerns, we propose PriviRec and PriviRec-k, two complementary recommendation frameworks. In PriviRec, we show that it is possible to decompose widely used filters so that they can be computed in a distributed setting using Secure Aggregation and a distributed version of the Randomized Power Method, without revealing individual users contributions. PriviRec-k extends this approach by having users securely aggregate low-rank projections of their contributions, enabling a tunable balance between communication overhead and recommendation accuracy. We demonstrate theoretically as well as experimentally on Gowalla, Yelp2018, and Amazon-Book that our methods achieve performance comparable to centralized state-of-the-art recommender systems and superior to decentralized ones, while preserving confidentiality and low communication and computational overheads.

Fichier principal
Vignette du fichier
CIKM___Privacy_preserving_recommender_system-17.pdf (698.17 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05308553 , version 1 (10-10-2025)

Licence

Identifiants

Citer

Julien Nicolas, César Sabater, Mohamed Maouche, Mark Coates, Sonia Ben Mokhtar. PriviRec: Confidential and Decentralized Graph Filtering for Recommender Systems. CIKM 2025 - ACM International Conference on Information and Knowledge Management, Nov 2025, Séoul, South Korea. pp.1-9, ⟨10.1145/3746252.3761152⟩. ⟨hal-05308553⟩
569 Consultations
311 Téléchargements

Altmetric

Partager

  • More