通过聚类优化联邦学习，降低AIoT设备能耗并加快收敛。
Energy-Efficient Federated Learning for AIoT using Clustering Methods
- 按标签分布聚类设备，减少分布式学习中的数据异构性。
- 相比现有方法，收敛更快且整体能耗更低。
- 适合资源受限的AIoT场景，如智能传感器网络。
尽管已有大量研究关注模型性能、收敛速度和通信效率，但现有文献普遍忽视了联邦学习（FL）在人工智能物联网（AIoT）场景下的能量消耗问题。本研究分析了FL过程中三大耗能环节：预处理、通信和本地学习，共同构成整体能耗。基于设备选择对分布式AIoT训练收敛速度的关键影响，我们提出两种基于聚类的方法，将标签分布相似的AIoT设备分组，形成近似异构的集群。该策略有效缓解了真实场景中常见的数据异构性问题。通过大规模数值实验，验证了所提聚类方法在保持低能耗的同时，通常实现更高的收敛速率，优于文献中其他近期方法。
原文摘要 · Abstract (English)
While substantial research has been devoted to optimizing model performance, convergence rates, and communication efficiency, the energy implications of federated learning (FL) within Artificial Intelligence of Things (AIoT) scenarios are often overlooked in the existing literature. This study examines the energy consumed during the FL process, focusing on three main energy-intensive processes: pre-processing, communication, and local learning, all contributing to the overall energy footprint. We rely on the observation that device/client selection is crucial for speeding up the convergence of model training in a distributed AIoT setting and propose two clustering-informed methods. These clustering solutions are designed to group AIoT devices with similar label distributions, resulting in clusters composed of nearly heterogeneous devices. Hence, our methods alleviate the heterogeneity often encountered in real-world distributed learning applications. Throughout extensive numerical experimentation, we demonstrate that our clustering strategies typically achieve high convergence rates while maintaining low energy consumption when compared to other recent approaches available in the literature.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。