mlsanityData to 7 Oct 2026

Privatized Graph Federated Learning

arXiv 2203.07105 ↗First posted 14 Mar 2022cs.LG cs.CRcited by 1

Not on the map. Why?

Abstract (arXiv)

Federated learning is a semi-distributed algorithm, where a server communicates with multiple dispersed clients to learn a global model. The federated architecture is not robust and is sensitive to communication and computational overloads due to its one-master multi-client structure. It can also be subject to privacy attacks targeting personal information on the communication links. In this work, we introduce graph federated learning (GFL), which consists of multiple federated units connected by a graph. We then show how graph homomorphic perturbations can be used to ensure the algorithm is differentially private. We conduct both convergence and privacy theoretical analyses and illustrate performance by means of computer simulations.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 15 of its 32 references that are in the map. First posted on arXiv 14 Mar 2022.

Builds on

15 of 32 references.

References · 15

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Deep Leakage from Gradientscited by 1,004
  3. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  4. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  5. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  6. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  7. 2019Client-Edge-Cloud Hierarchical Federated Learningcited by 202
  8. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
  9. 2019Federated Learning with Bayesian Differential Privacycited by 60
  10. 2021Decentralized Federated Learning: Balancing Communication and Computing Costscited by 54
  11. 2020Federated Learning under Importance Samplingcited by 26
  12. 2019Helen: Maliciously Secure Coopetitive Learning for Linear Modelscited by 20
3 more
  1. 2015Differentially Private Distributed Online Learningcited by 13
  2. 2021A Graph Federated Architecture with Privacy Preserving Learningcited by 10
  3. 2020Graph-Homomorphic Perturbations for Private Decentralized Learningcited by 6

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Momentum Benefits Non-IID Federated Learning Simply and Provablycited by 37