# A Graph Federated Architecture with Privacy Preserving Learning

arXiv: https://arxiv.org/abs/2104.13215 · HTML: https://mlsanity.com/paper/2104.13215/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 26 Apr 2021.

## Builds on (most cited first, 14 of 14)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [Exploiting Unintended Feature Leakage in Collaborative Learning](https://mlsanity.com/paper/1805.04049/) (2018)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning](https://mlsanity.com/paper/1702.07464/) (2017)
- [Client-Edge-Cloud Hierarchical Federated Learning](https://mlsanity.com/paper/1905.06641/) (2019)
- [LDP-Fed: Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2006.03637/) (2020)
- [Federated Learning with Bayesian Differential Privacy](https://mlsanity.com/paper/1911.10071/) (2019)
- [Federated Learning under Importance Sampling](https://mlsanity.com/paper/2012.07383/) (2020)
- [Helen: Maliciously Secure Coopetitive Learning for Linear Models](https://mlsanity.com/paper/1907.07212/) (2019)
- [Optimal Importance Sampling for Federated Learning](https://mlsanity.com/paper/2010.13600/) (2020)
- [Differentially Private Distributed Online Learning](https://mlsanity.com/paper/1505.06556/) (2015)
- [Graph-Homomorphic Perturbations for Private Decentralized Learning](https://mlsanity.com/paper/2010.12288/) (2020)

## Built on by (most cited first, 10 of 10)

- [Federated Graph Neural Networks: Overview, Techniques and Challenges](https://mlsanity.com/paper/2202.07256/) (2022)
- [Federated Graph Machine Learning: A Survey of Concepts, Techniques, and Applications](https://mlsanity.com/paper/2207.11812/) (2022)
- [Compression with Exact Error Distribution for Federated Learning](https://mlsanity.com/paper/2310.20682/) (2023)
- [Personalized Graph Federated Learning with Differential Privacy](https://mlsanity.com/paper/2306.06399/) (2023)
- [GLASU: A Communication-Efficient Algorithm for Federated Learning with Vertically Distributed Graph Data](https://mlsanity.com/paper/2303.09531/) (2023)
- [Privatized Graph Federated Learning](https://mlsanity.com/paper/2203.07105/) (2022)
- [Local Graph-homomorphic Processing for Privatized Distributed Systems](https://mlsanity.com/paper/2210.15414/) (2022)
- [GraMFedDHAR: Graph Based Multimodal Differentially Private Federated HAR](https://mlsanity.com/paper/2509.05671/) (2025)
- [Query-Efficient Adversarial Attack Against Vertical Federated Graph Learning](https://mlsanity.com/paper/2411.02809/) (2024)
- [Efficient and Privacy-Preserved Link Prediction via Condensed Graphs](https://mlsanity.com/paper/2503.12156/) (2025)

## Abstract (arXiv)

Federated learning involves a central processor that works with multiple agents to find a global model. The process consists of repeatedly exchanging estimates, which results in the diffusion of information pertaining to the local private data. Such a scheme can be inconvenient when dealing with sensitive data, and therefore, there is a need for the privatization of the algorithms. Furthermore, the current architecture of a server connected to multiple clients is highly sensitive to communication failures and computational overloads at the server. Thus in this work, we develop a private multi-server federated learning scheme, which we call graph federated learning. We use cryptographic and differential privacy concepts to privatize the federated learning algorithm that we extend to the graph structure. We study the effect of privatization on the performance of the learning algorithm for general private schemes that can be modeled as additive noise. We show under convexity and Lipschitz conditions, that the privatized process matches the performance of the non-private algorithm, even when we increase the noise variance.