Decentralized Semantic Federated Learning for Real-Time Public Safety Tasks: Challenges, Methods, and Directions

2025-04-07

AI Summary

To address the challenges of high communication energy consumption, strong resource heterogeneity, and the trade-off between semantic accuracy and efficiency in multi-region edge device collaboration for public safety tasks, this paper proposes a decentralized semantic federated learning framework. The method introduces a hierarchical semantic communication mechanism—enabling task-oriented encoding and selective transmission within base stations, and semantic aggregation with distributed consensus across base stations—alongside an energy-efficiency-aware two-tier aggregation scheme. Experiments on the BoWFire dataset demonstrate that the framework significantly reduces communication overhead and energy consumption (by 42.7% over baselines), improves fire detection real-time performance (latency reduced by 38.5%), and enhances accuracy (mAP increased by 6.2%). These results validate its effectiveness in supporting scalable deployment and practical application in large-scale heterogeneous wireless edge systems.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Multiagent Systems: Agent Communication
• Natural Language Processing: Safety and Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Public safety tasks rely on the collaborative functioning of multiple edge devices (MEDs) and base stations (BSs) in different regions, consuming significant communication energy and computational resources to execute critical operations like fire monitoring and rescue missions. Traditional federated edge computing (EC) methods require frequent central communication, consuming substantial energy and struggling with resource heterogeneity across devices, networks, and data. To this end, this paper introduces a decentralized semantic federated learning (DSFL) framework tailored for large-scale wireless communication systems and heterogeneous MEDs. The framework incorporates a hierarchical semantic communication (SC) scheme to extend EC coverage and reduce communication overhead. Specifically, the lower layer optimizes intra-BS communication through task-specific encoding and selective transmission under constrained networks, while the upper layer ensures robust inter-BS communication via semantic aggregation and distributed consensus across different regions. To further balance communication costs and semantic accuracy, an energy-efficient aggregation scheme is developed for both intra-BS and inter-BS communication. The effectiveness of the DSFL framework is demonstrated through a case study using the BoWFire dataset, showcasing its potential in real-time fire detection scenarios. Finally, we outlines open issues for edge intelligence and SC in public safety tasks.

Problem

• Reduces communication energy in decentralized federated learning systems
• Addresses resource heterogeneity in edge devices and networks
• Enhances real-time public safety tasks like fire detection

Innovation

• Decentralized semantic federated learning framework
• Hierarchical semantic communication scheme
• Energy-efficient semantic aggregation scheme