# Controlled privacy leakage propagation throughout overlapping grouped learning

arXiv: https://arxiv.org/abs/2503.04054 · HTML: https://mlsanity.com/paper/2503.04054/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 52 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 30 of 36)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Federated Multi-Task Learning](https://mlsanity.com/paper/1705.10467/) (2017)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [An Efficient Framework for Clustered Federated Learning](https://mlsanity.com/paper/2006.04088/) (2020)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [Adaptive Personalized Federated Learning](https://mlsanity.com/paper/2003.13461/) (2020)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [Three Approaches for Personalization with Applications to Federated Learning](https://mlsanity.com/paper/2002.10619/) (2020)
- [Robust Aggregation for Federated Learning](https://mlsanity.com/paper/1912.13445/) (2019)
- [Improving Federated Learning Personalization via Model Agnostic Meta Learning](https://mlsanity.com/paper/1909.12488/) (2019)
- [R'enyi Differential Privacy of the Sampled Gaussian Mechanism](https://mlsanity.com/paper/1908.10530/) (2019)
- [Federated Multi-Task Learning under a Mixture of Distributions](https://mlsanity.com/paper/2108.10252/) (2021)
- [When the Curious Abandon Honesty: Federated Learning Is Not Private](https://mlsanity.com/paper/2112.02918/) (2021)
- [FedALA: Adaptive Local Aggregation for Personalized Federated Learning](https://mlsanity.com/paper/2212.01197/) (2022)
- [Decentralized Collaborative Learning of Personalized Models over Networks](https://mlsanity.com/paper/1610.05202/) (2016)
- [Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services](https://mlsanity.com/paper/2303.16129/) (2023)
- [Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy](https://mlsanity.com/paper/2106.13673/) (2021)
- [Training Production Language Models without Memorizing User Data](https://mlsanity.com/paper/2009.10031/) (2020)
- [Individual Privacy Accounting via a Renyi Filter](https://mlsanity.com/paper/2008.11193/) (2020)
- [Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)](https://mlsanity.com/paper/2203.05363/) (2022)
- [Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs](https://mlsanity.com/paper/1901.08460/) (2019)
- [FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy](https://mlsanity.com/paper/2307.01217/) (2023)
- [Heterogeneous Differential Privacy](https://mlsanity.com/paper/1504.06998/) (2015)
- [Have it your way: Individualized Privacy Assignment for DP-SGD](https://mlsanity.com/paper/2303.17046/) (2023)

## Abstract (arXiv)

Federated Learning (FL) is the standard protocol for collaborative learning. In FL, multiple workers jointly train a shared model. They exchange model updates calculated on their data, while keeping the raw data itself local. Since workers naturally form groups based on common interests and privacy policies, we are motivated to extend standard FL to reflect a setting with multiple, potentially overlapping groups. In this setup where workers can belong and contribute to more than one group at a time, complexities arise in understanding privacy leakage and in adhering to privacy policies. To address the challenges, we propose differential private overlapping grouped learning (DPOGL), a novel method to implement privacy guarantees within overlapping groups. Under the honest-but-curious threat model, we derive novel privacy guarantees between arbitrary pairs of workers. These privacy guarantees describe and quantify two key effects of privacy leakage in DP-OGL: propagation delay, i.e., the fact that information from one group will leak to other groups only with temporal offset through the common workers and information degradation, i.e., the fact that noise addition over model updates limits information leakage between workers. Our experiments show that applying DP-OGL enhances utility while maintaining strong privacy compared to standard FL setups.