• Home
  • Search
  • FedKDShap: Enhancing Federated Learning via Shapley Values Driven Knowledge Distillation on Non-IID Data
  • Cite Icon3
  • https://doi.org/10.1145/3701716.3717645Copy DOI Icon

FedKDShap: Enhancing Federated Learning via Shapley Values Driven Knowledge Distillation on Non-IID Data

  • May 8, 2025
  • Nazmus Shakib Shadin +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Federated Learning (FL) has achieved significant popularity in privacy-preserving distributed learning, wherein data remains on edge devices, ensuring data security and user privacy. Regardless of its advantages, FL has considerable challenges, including the non-independent and identically distributed (non-IID) nature of data across clients, degradation in performance compared to centralized learning methods, and communication efficiency issues due to frequent exchanges of large model updates between clients and the server. To overcome these challenges, FL combined with knowledge distillation (KD), which is a decentralized learning methodology that facilitates collaborative model training across several devices or clients with data privacy. Traditional KD generally focuses on the transfer of knowledge through logits; however, this methodology omits the importance of intermediate feature representations within the model. To address this limitation, we propose incorporating Shapley Additive Explanations (SHAP) or Shapley values into knowledge distillation (KD) methods. Shapley values quantify feature importance, enabling the transfer of critical feature contributions, and thereby enhancing the effectiveness of KD. In this work, we propose a novel decentralized machine learning approach, named FedKDShap, refined federated learning with Shapley values-informed KD which prioritizes performance, interpretability, resource efficiency, and feature importance within the distillation process to optimize knowledge transfer from a high-capacity teacher model to a lightweight student model. This integration not only reduces communication demands on resource-constrained devices but also enhances model convergence in non-IID data settings by embedding Shapley values into the KD loss function. Our experiment leverages benchmark datasets to simulate real-world non-IID data distribution which also demonstrates that the FedKDShap method enhances model accuracy and outperforms state-of-the-art architectures. Our code repository is available at: https://github.com/shadhin39/FedKDShap

Similar Papers
  • PDF
  • Research Article
  • Citations16

Federated Learning for Medical Imaging Segmentation via Dynamic Aggregation on Non-IID Data Silos

  • Apr 03, 2023
  • Electronics
  • Liuyan Yang +3
  • Book Chapter

Edge Intelligence Architecture for Distributed and Federated Learning Systems

  • Dec 23, 2025
  • Pierluigi Dell'Acqua +2
  • Research Article
  • Citations11

Knowledge Distillation in Federated Learning: A Survey on Long Lasting Challenges and New Solutions

  • Jan 01, 2025
  • International Journal of Intelligent Systems
  • Laiqiao Qin +3
  • Research Article
  • Citations141

Semisupervised Federated-Learning-Based Intrusion Detection Method for Internet of Things

  • May 15, 2023
  • IEEE Internet of Things Journal
  • Ruijie Zhao +5
  • Conference Article
  • Citations13

A Semi-Supervised Federated Learning Scheme via Knowledge Distillation for Intrusion Detection

  • May 16, 2022
  • Ruijie Zhao +5
  • Research Article
  • Citations24

Resource-Efficient Federated Learning With Non-IID Data: An Auction Theoretic Approach

  • Dec 15, 2022
  • IEEE Internet of Things Journal
  • Eunil Seo +2
  • Research Article
  • Citations19

Knowledge Selection and Local Updating Optimization for Federated Knowledge Distillation With Heterogeneous Models

  • Jan 01, 2023
  • IEEE Journal of Selected Topics in Signal Processing
  • Dong Wang +3
  • Research Article
  • Citations15

Federated Learning Framework for Brain Tumor Detection Using MRI Images in Non-IID Data Distributions.

  • Mar 24, 2025
  • Journal of imaging informatics in medicine
  • Md Zahin Muntaqim +1
  • PDF
  • Research Article
  • Citations13

Optimizing Multi-Objective Federated Learning on Non-IID Data with Improved NSGA-III and Hierarchical Clustering

  • May 23, 2022
  • Symmetry
  • Jialin Zhong +4
  • Research Article
  • Citations9

PFedKD: Personalized Federated Learning via Knowledge Distillation Using Unlabeled Pseudo Data for Internet of Things

  • Jun 01, 2025
  • IEEE Internet of Things Journal
  • Hanxi Li +7
  • Research Article
  • Citations35

Communication-Efficient Federated Learning on Non-IID Data Using Two-Step Knowledge Distillation

  • Oct 01, 2023
  • IEEE Internet of Things Journal
  • Hui Wen +5
  • Research Article

Empowering Client Selection with Local Knowledge Distillation for Efficient Federated Learning in Non-IID Data

  • Oct 02, 2025
  • Journal of Internet Services and Applications
  • Aissa Hadj Mohamed +4
  • Research Article
  • Citations26

Affordable federated edge learning framework via efficient Shapley value estimation

  • May 11, 2023
  • Future Generation Computer Systems
  • Liguo Dong +4
  • Research Article
  • Citations16

When Federated Learning Meets Knowledge Distillation

  • Oct 01, 2024
  • IEEE Wireless Communications
  • Xiaoyi Pang +4
  • Research Article

التحديات والفرص في التعلم الفدرالي

  • Oct 01, 2022
  • International Science and Technology Journal
  • Ahmed S Alardawi +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.