Towards Heterogeneity-Aware and Energy-Efficient Topology Optimization for Decentralized Federated Learning in Edge Environment

2025/08/01 by Tiehua Zhang, Liu, Yuze, Zhang, Tiehua +8 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #IoT and Edge/Fog Computing #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data #Stochastic Gradient Optimization Techniques

paper · pdf · doi:10.48550/arxiv.2508.08278

openalex publication_date 2025/08/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Federated learning (FL) has emerged as a promising paradigm within edge computing (EC) systems, enabling numerous edge devices to collaboratively train artificial intelligence (AI) models while maintaining data privacy. To overcome the communication bottlenecks associated with centralized parameter servers, decentralized federated learning (DFL), which leverages peer-to-peer (P2P) communication, has been extensively explored in the research community. Although researchers design a variety of DFL approach to ensure model convergence, its iterative learning process inevitably incurs considerable cost along with the growth of model complexity and the number of participants. These costs are largely influenced by the dynamic changes of topology in each training round, particularly its sparsity and connectivity conditions. Furthermore, the inherent resources heterogeneity in the edge environments affects energy efficiency of learning process, while data heterogeneity degrades model performance. These factors pose significant challenges to the design of an effective DFL framework for EC systems. To this end, we propose Hat-DFed, a heterogeneity-aware and coset-effective decentralized federated learning (DFL) framework. In Hat-DFed, the topology construction is formulated as a dual optimization problem, which is then proven to be NP-hard, with the goal of maximizing model performance while minimizing cumulative energy consumption in complex edge environments. To solve this problem, we design a two-phase algorithm that dynamically constructs optimal communication topologies while unbiasedly estimating their impact on both model performance and energy cost. Additionally, the algorithm incorporates an importance-aware model aggregation mechanism to mitigate performance degradation caused by data heterogeneity.

Citations

• TDML -- A Trustworthy Distributed Machine Learning Framework
• FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-aware Model Update
• FedCache: A Knowledge Cache-driven Federated Learning Architecture for Personalized Edge Intelligence
• Adaptive Federated Learning via New Entropy Approach
• GNN at the Edge: Cost-Efficient Graph Neural Network Processing over Distributed Edge Servers
• Decentralized adaptive clustering of deep nets is beneficial for client collaboration
• An Adaptive Federated Relevance Framework for Spatial Temporal Graph Learning
• Towards Federated Learning on Time-Evolving Heterogeneous Data
• Decentralized federated learning of deep neural networks on non-iid data
• Federated Learning on Non-IID Data Silos: An Experimental Study
• Energy Efficient Federated Learning over Heterogeneous Mobile Devices via Joint Design of Weight Quantization and Wireless Transmission
• Privacy-preserving Decentralized Aggregation for Federated Learning
• TornadoAggregate: Accurate and Scalable Federated Learning via the Ring-Based Architecture
• Bandit Algorithms
• Decentralized gradient methods: does topology matter?
• Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing
• Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs
• How Energy-Efficient Can a Wireless Communication System Become?
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent
• Adam: A Method for Stochastic Optimization
• Dependent rounding and its applications to approximation algorithms

Cited by

• A Structure-Agnostic Co-Tuning Framework for LLMs and SLMs in Cloud-Edge Systems

Related

• Heterogeneity-Aware Resource Allocation and Topology Design for Hierarchical Federated Edge Learning
• Adaptive Configuration for Heterogeneous Participants in Decentralized Federated Learning
• Coordination-free Decentralised Federated Learning on Complex Networks: Overcoming Heterogeneity
• FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing
• A Comprehensive Survey on Joint Resource Allocation Strategies in Federated Edge Learning