Do Larger Batch Sizes Always Help? Revisiting Incentive-Driven Differential Privacy Federated Learning

Differential Privacy Federated Learning (DP-FL) combines Differential Privacy (DP) with Federated Learning (FL), enabling multiple clients to collaboratively train a shared model while protecting data privacy. However, introducing DP into FL will add noise to model parameters, which typically deteriorates model convergence. Although a recent work has revealed the compensation effect by increasing the total batch size, it overlooks the “generalization gap” phenomenon, which is induced by excessively large batch size and has been long discussed in the machine learning field. In order to avoid the other extreme, we strengthen several core components in, and propose an Incentive-driven Differential Privacy Federated Learning (IDP-FL) framework. First, instead of building all hopes on batch sizes, the proposed framework jointly considers the non-IID degrees of local data and clients’ privacy budgets, minimizing the difference between the optimal batch size for each selected client and its corresponding critical batch size. Second, we reconfigure the batch size for each selected client by balancing the negative impact of DP noise on convergence and of the “generalization gap” phenomenon. Finally, we design a Stackelberg game-based incentive mechanism that encourages clients to contribute computational resources, and prove the existence of a Stackelberg equilibrium to guarantee stability. Through numerical evaluations on real-world datasets, we show that our IDP-FL framework outperforms existing algorithms in terms of test accuracy and utility. Ablation studies further confirm the effectiveness of each component.

• Publication year

  2026

• Venue

  IEEE Transactions on Cognitive Communications and Networking

• Publication date

  Unknown publication date

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/TCCN.2025.3601898
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Joint Data Retransmission and Client Selection Optimization for Error-Tolerant Federated Learning in AAV Networks

  2025cited by this paper
• Incentive-Driven and Energy Efficient Federated Learning in Mobile Edge Networks

  2025cited by this paper
• CSRA: Robust Incentive Mechanism Design for Differentially Private Federated Learning

  2024cited by this paper
• Collaboration in Federated Learning With Differential Privacy: A Stackelberg Game Analysis

  2024influential reference
• Incentive Mechanism for Mobile Crowdsensing With Two-Stage Stackelberg Game

  2023cited by this paper
• Multifactor Incentive Mechanism for Federated Learning in IoT: A Stackelberg Game Approach

  2023cited by this paper
• Personalized Federated Learning With Differential Privacy and Convergence Guarantee

  2023cited by this paper
• Energy-Efficient GPU Clusters Scheduling for Deep Learning

  2023cited by this paper
• Heterogeneous Differential-Private Federated Learning: Trading Privacy for Utility Truthfully

  2023cited by this paper
• A Multi-agent Reinforcement Learning Approach for Efficient Client Selection in Federated Learning

  2022cited by this paper
• PyramidFL: a fine-grained client selection framework for efficient federated learning

  2022cited by this paper
• Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training

  2022cited by this paper
• Coordinated Batching and DVFS for DNN Inference on GPU Accelerators

  2022cited by this paper
• Energy-efficient client selection in federated learning with heterogeneous data on edge

  2022cited by this paper
• Incentive Mechanism for Differentially Private Federated Learning in Industrial Internet of Things

  2022cited by this paper
• FAIR: Quality-Aware Federated Learning with Precise User Incentive and Model Aggregation

  2021cited by this paper
• Sample-level Data Selection for Federated Learning

  2021cited by this paper
• Pain-FL: Personalized Privacy-Preserving Incentive for Federated Learning

  2021cited by this paper
• Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspective

  2021cited by this paper
• Federated Learning over Wireless Networks: Optimization Model Design and Analysis

  2019cited by this paper
• Federated Learning With Differential Privacy: Algorithms and Performance Analysis

  2019influential reference
• Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning

  2018cited by this paper
• Adaptive Federated Learning in Resource Constrained Edge Computing Systems

  2018cited by this paper
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

  2017cited by this paper
• Learning Differentially Private Recurrent Language Models

  2017cited by this paper
• Train longer, generalize better: closing the generalization gap in large batch training of neural networks

  2017cited by this paper
• Communication-Efficient Learning of Deep Networks from Decentralized Data

  2016cited by this paper
• Deep Learning with Differential Privacy

  2016cited by this paper
• On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima

  2016cited by this paper
• Membership Inference Attacks Against Machine Learning Models

  2016cited by this paper
• The Algorithmic Foundations of Differential Privacy

  2014cited by this paper
• A measurement study of GPU DVFS on energy conservation

  2013cited by this paper
• Stackelberg Voting Games: Computational Aspects and Paradoxes

  2010cited by this paper
• Learning Multiple Layers of Features from Tiny Images

  2009cited by this paper
• Survey of multi-objective optimization methods for engineering

  2004cited by this paper
• Gradient-based learning applied to document recognition

  1998cited by this paper

• No citing papers are available for this paper.