JSAM: Privacy Straggler-Resilient Joint Client Selection and Incentive Mechanism Design in Differentially Private Federated Learning

Ruichen Xu; Ying-Jun Angela Zhang; Jianwei Huang

cs.LGFeb 25, 2026

JSAM: Privacy Straggler-Resilient Joint Client Selection and Incentive Mechanism Design in Differentially Private Federated Learning

Authors: Ruichen Xu, Ying-Jun Angela Zhang, Jianwei Huang

Organizations: Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong · School of Science and Engineering, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network, and CSIJRI Joint Research Centre on Smart Energy Storage, The Chinese University of Hong Kong, Shenzhen, Guangdong, 518172, P.R. China

Abstract

Differentially private federated learning faces a fundamental tension: privacy protection mechanisms that safeguard client data simultaneously create quantifiable privacy costs that discourage participation, undermining the collaborative training process. Existing incentive mechanisms rely on unbiased client selection, forcing servers to compensate even the most privacy-sensitive clients ("privacy stragglers"), leading to systemic inefficiency and suboptimal resource allocation. We introduce JSAM (Joint client Selection and privacy compensAtion Mechanism), a Bayesian-optimal framework that simultaneously optimizes client selection probabilities and privacy compensation to maximize training effectiveness under budget constraints. Our approach transforms a complex 2N-dimensional optimization problem into an efficient three-dimensional formulation through novel theoretical characterization of optimal selection strategies. We prove that servers should preferentially select privacy-tolerant clients while excluding high-sensitivity participants, and uncover the counter-intuitive insight that clients with minimal privacy sensitivity may incur the highest cumulative costs due to frequent participation. Extensive evaluations on MNIST and CIFAR-10 demonstrate that JSAM achieves up to 15% improvement in test accuracy compared to existing unbiased selection mechanisms while maintaining cost efficiency across varying data heterogeneity levels.

Figures & tables

Fig. 1 : Differentially private federated learning employs noisy gradient updates to safeguard client privacy.

Fig. 2 : The "privacy straggler" effect. A single client with very low privacy budget ( $\epsilon_{k}$ ) forces the server to add excessive noise, degrade the model utility.

Mechanism	Client selection	Performance characterization	Client heterogeneity	Is privacy straggler-resilient?
[ 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 7 ]	Unbiased	Convergence analysis	Privacy budget	$\times$
[ 16 ]	Unbiased	Convergence analysis	Local dataset size	$\times$
[ 17 ]	Unbiased	Convergence analysis	Privacy budget	$\times$
[ 18 ]	Unbiased	Curve fitting	Privacy budget	$\times$
[ 19 ]	Bid based	Training cost	Training cost	$\times$
Our Method	Performance-aware (Flexible)	Convergence analysis	Privacy budget	$\checkmark$

TABLE I: Comparison of Incentive Mechanisms in DP-FL

Fig. 4 : Flow chart of problem reformulations.

Fig. 5 : An illustration of the structure of the optimal client selection probabilities with ten clients $(v_{1}<\cdots<v_{10})$ .

Panel of Figure 7 — Fig. 6 : Test accuracy versus monetary cost.

Mechanism	Monetary Cost	Non-iid Degree	Test Accuracy
	590.5221	$s=100$	77.37%
JSAM		$s=70$	76.13%
(Proposed)		$s=30$	68.20%
		$s=0$	50.06%
USBM	590.5437	$s=100$	77.45%
		$s=70$	75.93%

TABLE II : Test accuracy performance with large monetary costs (CIFAR-10).

Mechanism	Monetary Cost	Non-iid Degree	Test Accuracy
	590.5221	$s=100$	99.05%
JSAM		$s=70$	98.93%
(proposed)		$s=30$	98.88%
		$s=0$	98.13%
USBM	590.5437	$s=100$	98.99%
		$s=70$	98.94%

TABLE III : Test accuracy performance with large monetary costs (MNIST).

Fig. 7 : Monetary cost versus weighted parameter $\eta$ .

Fig. 8 : Number of selected clients versus monetary cost on CIFAR-10.

Incentive Mechanisms for Federated Learning

See all 10 papers

Tackling Privacy Heterogeneity in Differentially Private Federated Learning
Feb 26, 2026Ruichen Xu, Ying-Jun Angela Zhang, Jianwei HuangDifferentially Private Federated Learning Client Selection in Federated Learning
Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong · School of Science and Engineering, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network, and CSIJRI Joint Research Centre on Smart Energy Storage, The Chinese University of Hong Kong, Shenzhen, Guangdong, 518172, P.R. China
Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning
May 20, 2026Adda Akram Bendoukha, Heber Hwang Arcolezi, Nesrine Kaaniche +1Client Selection in Federated Learning Non-IID Federated Learning
Samovar, T´el´ecom SudParis, Institut Polytechnique de Paris, France · ´ETS Montr´eal · CEA-LIST
FEDBUD: Joint Incentive and Privacy Optimization for Resource-Constrained Federated Learning
Apr 12, 2026Tao Liu, Xuehe WangIncentive Mechanisms for Federated Learning Federated Learning
School of Artificial Intelligence, Sun Yat-sen University, Zhuhai 519082, China

Feb 26, 2026J/K move · Enter open · S save

Tackling Privacy Heterogeneity in Differentially Private Federated Learning

Ruichen Xu, Ying-Jun Angela Zhang, Jianwei Huang

Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong · School of Science and Engineering, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network, and CSIJRI Joint Research Centre on Smart Energy Storage, The Chinese University of Hong Kong, Shenzhen, Guangdong, 518172, P.R. China

Differentially Private Federated Learning Client Selection in Federated Learning Differential Privacy

Open paper AskPDF arXiv

Differentially private federated learning (DP-FL) enables clients to collaboratively train machine learning models while preserving the privacy of their local data. However, most existing DP-FL approaches assume that all clients share a uniform privacy budget, an assumption that does not hold in real-world scenarios where privacy requirements vary widely. This privacy heterogeneity poses a significant challenge: conventional client selection strategies, which typically rely on data quantity, cannot distinguish between clients providing high-quality updates and those introducing substantial noise due to strict privacy constraints. To address this gap, we present the first systematic study of privacy-aware client selection in DP-FL. We establish a theoretical foundation by deriving a convergence analysis that quantifies the impact of privacy heterogeneity on training error. Building on this analysis, we propose a privacy-aware client selection strategy, formulated as a convex optimization problem, that adaptively adjusts selection probabilities to minimize training error. Extensive experiments on benchmark datasets demonstrate that our approach achieves up to a 10% improvement in test accuracy on CIFAR-10 compared to existing baselines under heterogeneous privacy budgets. These results highlight the importance of incorporating privacy heterogeneity into client selection for practical and effective federated learning.

Abstract

Incentive Mechanisms for Federated Learning

Explore similar work

Tackling Privacy Heterogeneity in Differentially Private Federated Learning

Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning

FEDBUD: Joint Incentive and Privacy Optimization for Resource-Constrained Federated Learning