FedAtlas: a Privacy-Enhanced Federated Multi-Task Learning Framework Driven by Semantic Communication for Dual Heterogeneity
- 20 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. PP (5) , 1-14
Abstract
Federated Multi-Task Learning (FMTL) faces fundamental challenges arising from dual heterogeneity, including intrinsic task heterogeneity and communication challenges induced by heterogeneous system environments. Task heterogeneity often leads to negative knowledge transfer due to complex non-linear task relationships, while communication inefficiency constrains system scalability and training efficiency. Existing FMTL methods typically rely on shallow task relation modeling and overlook the structural nature of task dependencies. To address these challenges, we propose FedAtlas, a structure aware and privacy-enhanced FMTL framework that explicitly constructs a global non-linear task relationship atlas through an adaptive structure inference module. Guided by the inferred atlas, FedAtlas adopts a structure-aware dual-level aggregation strategy to jointly optimize shared encoders and personalized decoders, effectively mitigating negative transfer while preserving task-specific specialization. Furthermore, FedAtlas integrates a semantic communication mechanism to alleviate communication inefficiency under heterogeneous system conditions. By leveraging client-specific vector quantization codebook, the proposed design enables compact semantic feature transmission while providing intrinsic privacy protection without explicit noise injection. Extensive experiments demonstrate that FedAtlas outperforms state-of-the-art FMTL methods, showing 4.82% improvement in performance and efficiency trade-off.Keywords
Funding Information
- National Natural Science Foundation of China (62302203)
- Natural Science Foundation of Fujian Province (2025J02019)
- Fujian Provincial Special Research Program on Science and Technology for Policing (2025YZ040003)
- Fujian Provincial Industrial Technology Development and Application Program (2025H0043)
This publication has 19 references indexed in Scilit:
- Toward Personalized Federated Meta-Learning With Constrained Hypernetwork on Non-IID DataIEEE Transactions on Computers, 2025
- Fedhca2: Towards Hetero-Client Federated Multi-Task Learning2024
- Communication-efficient federated learning via knowledge distillationNature Communications, 2022
- FedGraph: Federated Graph Learning With Intelligent SamplingIEEE Transactions on Parallel and Distributed Systems, 2021
- Deep Learning Enabled Semantic Communication SystemsIEEE Transactions on Signal Processing, 2021
- Clustered Federated Learning: Model-Agnostic Distributed Multitask Optimization Under Privacy ConstraintsIEEE Transactions on Neural Networks and Learning Systems, 2020
- DeepJSCC-f: Deep Joint Source-Channel Coding of Images With FeedbackIEEE Journal on Selected Areas in Information Theory, 2020
- Deep Joint Source-Channel Coding for Wireless Image TransmissionIEEE Transactions on Cognitive Communications and Networking, 2019
- Deep Learning for Joint Source-Channel Coding of Text2018
- Semantic Communications2010