Towards Efficient and Adaptive Traffic Classification: A Knowledge Distillation-Based Personalized Federated Learning Framework

Traffic classification plays a crucial role in optimizing network management, enhancing security, and enabling intelligent resource allocation in distributed network systems. However, traditional Federated Learning (FL) approaches struggle with domain heterogeneity, as network traffic characteristics vary significantly across different domains due to diverse infrastructure, applications, and usage patterns. This results in degraded performance when applying a single global model across all domains. To overcome this challenge, we propose KD-PFL-TC, a Knowledge Distillation-based Personalized Federated Learning framework for Traffic Classification, aimed to balance global knowledge sharing with personalized model adaptation in heterogeneous network environments. Our approach leverages knowledge distillation to enable collaborative learning without directly sharing raw data, preserving privacy while mitigating the negative effects of domain shifts. Each domain refines its local model by integrating insights from a global model and peer domains while maintaining its unique traffic distribution. To further enhance performance, we introduce an adaptive distillation strategy that dynamically adjusts the influence of global, peer, and local knowledge based on the similarity between traffic distributions, ensuring optimal knowledge transfer designed to each domain’s characteristics. Extensive experiments on real-world traffic datasets show that KD–PFL–TC maintains 88.0% accuracy under high heterogeneity (vs. 75.0% for FedAvg) while reducing communication overhead by ~60%, delivering an efficient and robust solution for large-scale, heterogeneous networks.

• Publication year

  2026

• Venue

  IEEE Transactions on Network and Service Management

• Publication date

  Unknown publication date

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1109/TNSM.2025.3629241
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• FedBKD: Heterogenous Federated Learning via Bidirectional Knowledge Distillation for Modulation Classification in IoT-Edge System

  2023cited by this paper
• A survey on federated learning: challenges and applications

  2022cited by this paper
• On Bridging Generic and Personalized Federated Learning for Image Classification

  2022cited by this paper
• Federated Learning for Internet of Things: A Comprehensive Survey

  2021cited by this paper
• Data-Free Knowledge Distillation for Heterogeneous Federated Learning

  2021cited by this paper
• Model-Contrastive Federated Learning

  2021cited by this paper
• Towards Personalized Federated Learning

  2021cited by this paper
• Personalized Federated Learning with Moreau Envelopes

  2020cited by this paper
• Personalized Federated Learning: A Meta-Learning Approach

  2020cited by this paper
• Ditto: Fair and Robust Federated Learning Through Personalization

  2020cited by this paper
• Adaptive Personalized Federated Learning

  2020cited by this paper
• Ensemble Distillation for Robust Model Fusion in Federated Learning

  2020cited by this paper
• Clustered Federated Learning: Model-Agnostic Distributed Multitask Optimization Under Privacy Constraints

  2019cited by this paper
• Mobile Encrypted Traffic Classification Using Deep Learning: Experimental Evaluation, Lessons Learned, and Challenges

  2019cited by this paper
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey

  2019cited by this paper
• Deep Learning for Encrypted Traffic Classification: An Overview

  2018cited by this paper
• Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization

  2018cited by this paper
• Federated Optimization in Heterogeneous Networks

  2018cited by this paper
• Federated Multi-Task Learning

  2017cited by this paper
• Deep packet: a novel approach for encrypted traffic classification using deep learning

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

  2016cited by this paper
• UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set)

  2015cited by this paper
• Distilling the Knowledge in a Neural Network

  2015cited by this paper
• A survey of techniques for internet traffic classification using machine learning

  2008cited by this paper
• CLASSIFICATION

  1931cited by this paper

• No citing papers are available for this paper.