# Federated Learning With Individualized Privacy Through Client Sampling

arXiv: https://arxiv.org/abs/2501.17634 · HTML: https://mlsanity.com/paper/2501.17634/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 29 Jan 2025.

## Builds on (most cited first, 15 of 15)

- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [Differentially Private Learning with Adaptive Clipping](https://mlsanity.com/paper/1905.03871/) (2019)
- [How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy](https://mlsanity.com/paper/2303.00654/) (2023)
- [When the Curious Abandon Honesty: Federated Learning Is Not Private](https://mlsanity.com/paper/2112.02918/) (2021)
- [When Machine Learning Meets Privacy: A Survey and Outlook](https://mlsanity.com/paper/2011.11819/) (2020)
- [LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2007.15789/) (2020)
- [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)
- [Federated Learning with Heterogeneous Differential Privacy](https://mlsanity.com/paper/2110.15252/) (2021)
- [Slice it up: Unmasking User Identities in Smartwatch Health Data](https://mlsanity.com/paper/2308.08310/) (2023)
- [Assessing the Impact of Image Dataset Features on Privacy-Preserving Machine Learning](https://mlsanity.com/paper/2409.01329/) (2024)

## Built on by (most cited first, 1 of 1)

- [Learning from Anonymized and Incomplete Tabular Data](https://mlsanity.com/paper/2602.01217/) (2026)

## Abstract (arXiv)

With growing concerns about user data collection, individualized privacy has emerged as a promising solution to balance protection and utility by accounting for diverse user privacy preferences. Instead of enforcing a uniform level of anonymization for all users, this approach allows individuals to choose privacy settings that align with their comfort levels. Building on this idea, we propose an adapted method for enabling Individualized Differential Privacy (IDP) in Federated Learning (FL) by handling clients according to their personal privacy preferences. By extending the SAMPLE algorithm from centralized settings to FL, we calculate client-specific sampling rates based on their heterogeneous privacy budgets and integrate them into a modified IDP-FedAvg algorithm. We test this method under realistic privacy distributions and multiple datasets. The experimental results demonstrate that our approach achieves clear improvements over uniform DP baselines, reducing the trade-off between privacy and utility. Compared to the alternative SCALE method in related work, which assigns differing noise scales to clients, our method performs notably better. However, challenges remain for complex tasks with non-i.i.d. data, primarily stemming from the constraints of the decentralized setting.