跳到正文
返回论文列表
cs.LG提交于 已译

面向工业物联网的过程挖掘驱动联邦异常检测

Process Mining-Enabled Federated Anomaly Detection for the Industrial IoT

Francesco Vitale · Salvatore Bramante · Francesco Flammini · Hangli Ge

中文摘要

联邦异常检测能整合不同节点的本地数据洞察以降低误报,但本质上难以应对非独立同分布(non-IID)数据。实际工业物联网工厂常在多变工况与多样环境现象下运行,导致被监测时间序列显著异质。此时标准联邦学习方法无法进行顾及跨节点差异的细致聚合,最终抬高误报率。为此,提出一种过程挖掘(process mining)方法,以全局节点提供的参考评估本地节点数据的相似度;全局节点利用这些相似度指标在聚合时动态加权本地模型,生成个性化更新并分发到网络。使用来自不同工况制造工厂的工业物联网时间序列数据评估。实验表明,该过程挖掘驱动的联邦异常检测流程性能更优:相比孤立本地训练基线与标准FedAvg,F1-score分别相对提升46.52%和11.99%,同时相比标准联邦聚合误报相对减少51.24%。

关键要点

  1. 01工业物联网时间序列存在显著非独立同分布异质性,标准联邦学习聚合会抬高误报率。
  2. 02用过程挖掘计算本地节点数据与全局参考的相似度,据此动态加权聚合本地模型。
  3. 03全局节点生成个性化更新并分发,缓解跨节点差异带来的聚合失准。
  4. 04在制造工厂时间序列数据上,F1-score较本地训练与FedAvg分别相对提升46.52%和11.99%。
  5. 05相比标准联邦聚合,误报相对减少51.24%。

解读

尚无解读。

原始英文摘要

arXiv:2611.17869v1 Announce Type: new Abstract: While federated anomaly detection enables the integration of local data insights across diverse nodes to reduce false positives, it inherently struggles with non-IID data. In practice, industrial IoT plants often operate under varying conditions and experience diverse environmental phenomena, resulting in significant heterogeneity in the monitored time series. In such settings, standard federated learning approaches fail to perform nuanced aggregation that accounts for these cross-node differences, ultimately leading to increased false positive rates. In this paper, we propose a process mining approach to evaluate the similarity of local node data against a reference provided by a global node. The global node utilizes these similarity metrics to dynamically weight local models during aggregation, producing personalized updates distributed across the network. We evaluate our approach using industrial IoT time-series data collected from manufacturing plants operating under distinct conditions. Experimental results demonstrate that our process mining-enabled federated anomaly detection pipeline achieves superior performance, yielding a 46.52% and 11.99% relative improvement in F1-score compared to isolated local training baselines and standard FedAvg, respectively, alongside a 51.24% relative reduction in false positives over standard federated aggregation.

同方向论文 · cs.LG

查看全部 →