mlsanityData to 14 Oct 2026

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

arXiv 2508.08278 ↗First posted 1 Aug 2025cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 25 of its 52 references that are in the map. First posted on arXiv 1 Aug 2025.

Builds on

25 of 52 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  5. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 502
  6. 2018Stochastic Gradient Push for Distributed Deep Learningcited by 152
  7. 2019Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computingcited by 152
  8. 2018Learning Private Neural Language Modeling with Attentive Aggregationcited by 49
  9. 2019Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphscited by 36
  10. 2020Decentralized gradient methods: does topology matter?cited by 35
  11. 2023FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-aware Model Updatecited by 32
  12. 2021Decentralized federated learning of deep neural networks on non-iid datacited by 25
13 more
  1. 2020Energy Efficient Federated Learning over Heterogeneous Mobile Devices via Joint Design of Weight Quantization and Wireless Transmissioncited by 23
  2. 2021Towards Federated Learning on Time-Evolving Heterogeneous Datacited by 23
  3. 2023Topology-aware Federated Learning in Edge Computing: A Comprehensive Surveycited by 23
  4. 2023FedCache: A Knowledge Cache-driven Federated Learning Architecture for Personalized Edge Intelligencecited by 17
  5. 2020TornadoAggregate: Accurate and Scalable Federated Learning via the Ring-Based Architecturecited by 12
  6. 2022GNN at the Edge: Cost-Efficient Graph Neural Network Processing over Distributed Edge Serverscited by 11
  7. 2020Privacy-preserving Decentralized Aggregation for Federated Learningcited by 10
  8. 2022An Adaptive Federated Relevance Framework for Spatial Temporal Graph Learningcited by 7
  9. 2022Decentralized adaptive clustering of deep nets is beneficial for client collaborationcited by 7
  10. 2024Towards Multi-agent Reinforcement Learning based Traffic Signal Control through Spatio-temporal Hypergraphscited by 5
  11. 2023Adaptive Federated Learning via New Entropy Approachcited by 3
  12. 2023A Carbon Tracking Model for Federated Learning: Impact of Quantization and Sparsificationcited by 3
  13. 2024TDML -- A Trustworthy Distributed Machine Learning Frameworkcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025A Structure-Agnostic Co-Tuning Framework for LLMs and SLMs in Cloud-Edge Systemscited by 1
  2. 2026Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuningcited by 0
  3. 2026FL-MAESTRO: Multi-Agent LLM Orchestration for Resource-Constrained Federated Learningcited by 0