Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data

• URL: http://arxiv.org/abs/2508.14769v1
• Date: Wed, 20 Aug 2025 15:17:59 GMT
• Title: Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data
• Authors: Ahmed Mujtaba, Gleb Radchenko, Radu Prodan, Marc Masana,
• Abstract summary: Federated learning has emerged as a promising collaborative machine learning approach.<n>We propose a robust, resource-efficient EdgeFD method that reduces the complexity of the client-side density ratio estimation.<n>We evaluate EdgeFD across diverse practical scenarios, including strong non-IID, weak non-IID, and IID data distributions on clients, without requiring a pre-trained teacher model on the server for knowledge distillation.
• Score: 4.758807762853925
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated distillation has emerged as a promising collaborative machine learning approach, offering enhanced privacy protection and reduced communication compared to traditional federated learning by exchanging model outputs (soft logits) rather than full model parameters. However, existing methods employ complex selective knowledge-sharing strategies that require clients to identify in-distribution proxy data through computationally expensive statistical density ratio estimators. Additionally, server-side filtering of ambiguous knowledge introduces latency to the process. To address these challenges, we propose a robust, resource-efficient EdgeFD method that reduces the complexity of the client-side density ratio estimation and removes the need for server-side filtering. EdgeFD introduces an efficient KMeans-based density ratio estimator for effectively filtering both in-distribution and out-of-distribution proxy data on clients, significantly improving the quality of knowledge sharing. We evaluate EdgeFD across diverse practical scenarios, including strong non-IID, weak non-IID, and IID data distributions on clients, without requiring a pre-trained teacher model on the server for knowledge distillation. Experimental results demonstrate that EdgeFD outperforms state-of-the-art methods, consistently achieving accuracy levels close to IID scenarios even under heterogeneous and challenging conditions. The significantly reduced computational overhead of the KMeans-based estimator is suitable for deployment on resource-constrained edge devices, thereby enhancing the scalability and real-world applicability of federated distillation. The code is available online for reproducibility.

Related papers

• Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection [53.45696787935487]
  Federated Learning (FL) enables collaborative model training across large-scale distributed service nodes.<n>In real-world service-oriented deployments, data generated by heterogeneous users, devices, and application scenarios are inherently non-IID.<n>We propose FLood, a novel FL framework inspired by out-of-distribution (OOD) detection.
  arXiv  Detail & Related papers  (2026-02-01T05:54:59Z)
• Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems [54.916243942641444]
  Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications.<n>We study an edge-cloud-expert cascaded LLM-based knowledge system that supports decision-making through a question-and-answer pipeline.
  arXiv  Detail & Related papers  (2025-12-23T03:10:09Z)
• Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout [62.73150122809138]
  Federated Learning (FL) is a promising distributed machine learning approach that enables collaborative training of a global model using multiple edge devices.<n>We propose the FedDHAD FL framework, which comes with two novel methods: Dynamic Heterogeneous model aggregation (FedDH) and Adaptive Dropout (FedAD)<n>The combination of these two methods makes FedDHAD significantly outperform state-of-the-art solutions in terms of accuracy (up to 6.7% higher), efficiency (up to 2.02 times faster), and cost (up to 15.0% smaller)
  arXiv  Detail & Related papers  (2025-07-14T16:19:00Z)
• Online federated learning framework for classification [7.613977984287604]
  We develop a novel online federated learning framework for classification.<n>We handle streaming data from multiple clients while ensuring data privacy and computational efficiency.<n>Our approach delivers high classification accuracy, significant computational efficiency gains, and substantial savings in data storage requirements compared to existing methods.
  arXiv  Detail & Related papers  (2025-03-19T13:50:19Z)
• HFedCKD: Toward Robust Heterogeneous Federated Learning via Data-free Knowledge Distillation and Two-way Contrast [10.652998357266934]
  We propose a system heterogeneous federation method based on data-free knowledge distillation and two-way contrast (HFedCKD)<n>HFedCKD effectively alleviates the knowledge offset caused by a low participation rate under data-free knowledge distillation and improves the performance and stability of the model.<n>We conduct extensive experiments on image and IoT datasets to comprehensively evaluate and verify the generalization and robustness of the proposed HFedCKD framework.
  arXiv  Detail & Related papers  (2025-03-09T08:32:57Z)
• Secure Federated Data Distillation [2.5311562666866494]
  We propose a Secure Federated Data Distillation (SFDD) framework to decentralize the distillation process while preserving privacy.<n>We leverage the gradient-matching-based distillation method, adapting it for a distributed setting where clients contribute to the distillation process without sharing raw data.<n>We create an optimized Local Differential Privacy approach, called LDPO-RLD, to make our approach resilient to inference attacks.
  arXiv  Detail & Related papers  (2025-02-19T13:54:44Z)
• Client-Centric Federated Adaptive Optimization [78.30827455292827]
  Federated Learning (FL) is a distributed learning paradigm where clients collaboratively train a model while keeping their own data private.<n>We propose Federated-Centric Adaptive Optimization, which is a class of novel federated optimization approaches.
  arXiv  Detail & Related papers  (2025-01-17T04:00:50Z)
• Learnable Sparse Customization in Heterogeneous Edge Computing [27.201987866208484]
  We propose Learnable Personalized Sparsification for heterogeneous Federated learning (FedLPS)<n>FedLPS learns the importance of model units on local data representation and derives an importance-based sparse pattern with minimals to accurately extract personalized data features.<n>Experiments show that FedLPS outperforms status quo approaches in accuracy and training costs.
  arXiv  Detail & Related papers  (2024-12-10T06:14:31Z)
• Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
  We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
  arXiv  Detail & Related papers  (2023-05-01T20:04:46Z)
• Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good Teacher [52.2926020848095]
  Federated learning is vulnerable to white-box attacks and struggles to adapt to heterogeneous clients. This paper proposes a selective knowledge sharing mechanism for FD, termed Selective-FD.
  arXiv  Detail & Related papers  (2023-04-04T12:04:19Z)
• Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillation [20.24005399782197]
  Federated learning is a privacy-preserving machine learning paradigm. Recent proxy-data-free FD approaches can eliminate the need for additional public data, but suffer from remarkable discrepancy among local knowledge. We propose a proxy-data-free FD algorithm based on distributed knowledge congruence (FedDKC)
  arXiv  Detail & Related papers  (2022-04-14T15:39:22Z)
• Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning [61.488646649045215]
  Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices)
  arXiv  Detail & Related papers  (2021-11-28T19:03:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.