联邦预测性维护系统中端侧生成模型的权衡分析
On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems
AI 导读
arXiv 论文系统分析了 VAE、GAN 和 Diffusion Models 在联邦预测性维护（PdM）中的表现，比较全联邦与部分联邦设置下的性能与通信开销。实验覆盖 5 个客户端和 2 个工业时序基准：GAN 全联邦比本地独立训练提升异常检测效果但稳健性不及 VAE 和 DDPM；Diffusion Model 仅共享解码器即可匹配全联邦效果并大幅降低通信负载。
正文 · 原文
Abstract:Federated Learning (FL) has emerged as a promising paradigm for preserving client data ownership and control over distributed Internet of Things (IoT) environments. While discriminative models dominate most FL use cases, recent advances in generative models - such as Variational Autoencoders (VAE), Generative Adversarial Networks (GAN), and Diffusion Models (DM) - offer new opportunities for unsupervised anomaly detection in time series analysis, with relevant applications in predictive maintenance (PdM) in critical industrial infrastructures. In this work, we present a comprehensive analysis of VAEs, GANs, and DMs in the context of federated PdM. We analyze their performance and communication overhead under both full and partial federation setups, where only subsets of model components are shared. Building on split-parameter personalized FL, this paper provides an empirical instantiation of shared/private parameter partitioning for unsupervised generative Time-Series Anomaly Detection (TSAD), mapping the split to analysis and synthesis modules across the generative architectures. Our experiments over five clients and two industrial time-series benchmarks reveal distinct trade-offs in model utility, stability, and communication efficiency in heterogeneous cross-silo FL. For the evaluated GAN-based configurations, full federation improves final anomaly-detection utility relative to independent local training, although these models remain less robust than the VAE- and DDPM-based alternatives. For DMs, decoder sharing matches full federation while substantially reducing the communication payload.
| Comments: | Published in IEEE Internet of Things Journal, 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.07860 [cs.LG] |
| (or arXiv:2605.07860v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.07860 arXiv-issued DOI via DataCite |
|
| Journal reference: | IEEE Internet of Things Journal, 2026 |
| Related DOI: | https://doi.org/10.1109/JIOT.2026.3739066
DOI(s) linking to related resources |
Submission history
From: Usevalad Milasheuski [view email]
[v1]
Fri, 8 May 2026 15:20:22 UTC (2,782 KB)
[v2]
Tue, 27 Oct 2026 10:33:35 UTC (2,325 KB)
来源：arXiv cs.AI · arxiv.org