mlsanityData to 14 Oct 2026

Stronger Privacy for Federated Collaborative Filtering with Implicit Feedback

arXiv 2105.03941 ↗First posted 9 May 2021cs.LG cs.CR cs.MAcited by 26

Not on the map. Why?

Abstract (arXiv)

Recommender systems are commonly trained on centrally collected user interaction data like views or clicks. This practice however raises serious privacy concerns regarding the recommender's collection and handling of potentially sensitive data. Several privacy-aware recommender systems have been proposed in recent literature, but comparatively little attention has been given to systems at the intersection of implicit feedback and privacy. To address this shortcoming, we propose a practical federated recommender system for implicit data under user-level local differential privacy (LDP). The privacy-utility trade-off is controlled by parameters ε and k, regulating the per-update privacy budget and the number of ε-LDP gradient updates sent by each user respectively. To further protect the user's privacy, we introduce a proxy network to reduce the fingerprinting surface by anonymizing and shuffling the reports before forwarding them to the recommender. We empirically demonstrate the effectiveness of our framework on the MovieLens dataset, achieving up to Hit Ratio with K=10 (HR@10) 0.68 on 50k users with 5k items. Even on the full dataset, we show that it is possible to achieve reasonable utility with HR@10>0.5 without compromising user privacy.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 15 of its 38 references that are in the map. First posted on arXiv 9 May 2021.

Builds on

15 of 38 references.

References · 15

  1. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  2. 2017Neural Collaborative Filteringcited by 1,111
  3. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
  4. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 272
  5. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 246
  6. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 164
  7. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 132
  8. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 130
  9. 2019Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation Systemcited by 79
  10. 2020LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacycited by 64
  11. 2019Collecting and Analyzing Multidimensional Data with Local Differential Privacycited by 49
  12. 2020FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selectioncited by 36
3 more
  1. 2019Federated Heavy Hitters Discovery with Differential Privacycited by 32
  2. 2016Collecting and Analyzing Data from Smart Device Users with Local Differential Privacycited by 25
  3. 2015Don't let Google know I'm lonely!cited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 10; 2023: 9; 2024: 3; 2025: 3; 2026: 1.

26 papers.

Sort:

By area:

  1. 2022FedRecAttack: Model Poisoning Attack to Federated Recommendationcited by 20
  2. 2023Dual Personalization on Federated Recommendationcited by 19
  3. 2022Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient Ensemblingcited by 9
  4. 2023Federated Recommendation with Additive Personalizationcited by 9
  5. 2022Auxo: Efficient Federated Learning via Scalable Client Clusteringcited by 8
  6. 2024A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applicationscited by 8
  7. 2023User Consented Federated Recommender System Against Personalized Attribute Inference Attackcited by 7
  8. 2022FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Datacited by 6
  9. 2022FedSPLIT: One-Shot Federated Recommendation System Based on Non-negative Joint Matrix Factorization and Knowledge Distillationcited by 5
  10. 2022Cali3F: Calibrated Fast Fair Federated Recommendation Systemcited by 5
  11. 2022FedGRec: Federated Graph Recommender System with Lazy Update of Latent Embeddingscited by 4
  12. 2023FedPDD: A Privacy-preserving Double Distillation Framework for Cross-silo Federated Recommendationcited by 4
14 more
  1. 2023Federated Learning on Non-iid Data via Local and Global Distillationcited by 4
  2. 2024Efficient and Robust Regularized Federated Recommendationcited by 4
  3. 2025Preventing the Popular Item Embedding Based Attack in Federated Recommendationscited by 3
  4. 2022Modeling Global Distribution for Federated Learning with Label Distribution Skewcited by 2
  5. 2022Smart Multi-tenant Federated Learningcited by 1
  6. 2023Federated Privacy-preserving Collaborative Filtering for On-Device Next App Predictioncited by 1
  7. 2025UFGraphFR: Graph Federation Recommendation System based on User Text description featurescited by 1
  8. 2022Horizontal Federated Learning and Secure Distributed Training for Recommendation System with Intel SGXcited by 0
  9. 2023DRIFT: A Federated Recommender System with Implicit Feedback on the Itemscited by 0
  10. 2023FedRec+: Enhancing Privacy and Addressing Heterogeneity in Federated Recommendation Systemscited by 0
  11. 2023Heterogeneous federated collaborative filtering using FAIR: Federated Averaging in Random Subspacescited by 0
  12. 2024Navigating the Future of Federated Recommendation Systems with Foundation Modelscited by 0
  13. 2025A Scenario-Oriented Survey of Federated Recommender Systems: Techniques, Challenges, and Future Directionscited by 0
  14. 2026Empowering Contrastive Federated Sequential Recommendation with LLMscited by 0