# The Power of Bias: Optimizing Client Selection in Federated Learning with Heterogeneous Differential Privacy

arXiv: https://arxiv.org/abs/2408.08642 · HTML: https://mlsanity.com/paper/2408.08642/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 16 Aug 2024.

## Builds on (most cited first, 21 of 21)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [The Future of Digital Health with Federated Learning](https://mlsanity.com/paper/2003.08119/) (2020)
- [Fair Resource Allocation in Federated Learning](https://mlsanity.com/paper/1905.10497/) (2019)
- [Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning](https://mlsanity.com/paper/2108.10241/) (2021)
- [Membership Inference Attacks by Exploiting Loss Trajectory](https://mlsanity.com/paper/2208.14933/) (2022)
- [Federated Accelerated Stochastic Gradient Descent](https://mlsanity.com/paper/2006.08950/) (2020)
- [Privacy Preserving Machine Learning: Threats and Solutions](https://mlsanity.com/paper/1804.11238/) (2018)
- [Differentially Private Federated Learning on Heterogeneous Data](https://mlsanity.com/paper/2111.09278/) (2021)
- [Eluding Secure Aggregation in Federated Learning via Model Inconsistency](https://mlsanity.com/paper/2111.07380/) (2021)
- [TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels](https://mlsanity.com/paper/2207.06343/) (2022)
- [Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors](https://mlsanity.com/paper/2112.06872/) (2021)
- [The Value of Collaboration in Convex Machine Learning with Differential Privacy](https://mlsanity.com/paper/1906.09679/) (2019)
- [DELTA: Diverse Client Sampling for Fasting Federated Learning](https://mlsanity.com/paper/2205.13925/) (2022)
- [Membership Inference Attacks and Generalization: A Causal Perspective](https://mlsanity.com/paper/2209.08615/) (2022)
- [Compression Boosts Differentially Private Federated Learning](https://mlsanity.com/paper/2011.05578/) (2020)
- [Federated Learning with Heterogeneous Differential Privacy](https://mlsanity.com/paper/2110.15252/) (2021)
- [A Joint Approach to Local Updating and Gradient Compression for Efficient Asynchronous Federated Learning](https://mlsanity.com/paper/2407.05125/) (2024)

## Built on by (most cited first, 2 of 2)

- [Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacy](https://mlsanity.com/paper/2505.13655/) (2025)
- [IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning](https://mlsanity.com/paper/2606.02563/) (2026)

## Abstract (arXiv)

To preserve the data privacy, the federated learning (FL) paradigm emerges in which clients only expose model gradients rather than original data for conducting model training. To enhance the protection of model gradients in FL, differentially private federated learning (DPFL) is proposed which incorporates differentially private (DP) noises to obfuscate gradients before they are exposed. Yet, an essential but largely overlooked problem in DPFL is the heterogeneity of clients' privacy requirement, which can vary significantly between clients and extremely complicates the client selection problem in DPFL. In other words, both the data quality and the influence of DP noises should be taken into account when selecting clients. To address this problem, we conduct convergence analysis of DPFL under heterogeneous privacy, a generic client selection strategy, popular DP mechanisms and convex loss. Based on convergence analysis, we formulate the client selection problem to minimize the value of loss function in DPFL with heterogeneous privacy, which is a convex optimization problem and can be solved efficiently. Accordingly, we propose the DPFL-BCS (biased client selection) algorithm. The extensive experiment results with real datasets under both convex and non-convex loss functions indicate that DPFL-BCS can remarkably improve model utility compared with the SOTA baselines.