Anomaly and missing data constitute a thorny problem in industrial applications. In recent years, deep learning enabled anomaly detection has emerged as a critical direction, however the improved detection accuracy is achieved with the utilization of large neural networks, increasing their storage and computational cost. Moreover, the data collected in edge devices contain user privacy, introducing challenges that can be successfully addressed by the privacy-preserving distributed paradigm, known as federated learning (FL). This framework allows edge devices to train and exchange models increasing also the communication cost. Thus, to deal with the increased communication, processing and storage challenges of the FL based deep anomaly detection NN pruning is expected to have significant benefits towards reducing the processing, storage and communication complexity. With this focus, a novel compression-based optimization problem is proposed at the server-side of a FL paradigm that fusses the received local models broadcast and performs pruning generating a more compressed model. Experiments in the context of anomaly detection and missing value imputation demonstrate that the proposed FL scenario along with the proposed compressed-based method are able to achieve high compression rates (more than $99.7\%$) with negligible performance losses (less than $1.18\%$ ) as compared to the centralized solutions.

翻译：异常与缺失数据是工业应用中的一个棘手问题。近年来，基于深度学习的异常检测已成为一个重要方向，但检测精度的提升依赖于大型神经网络的使用，从而增加了存储与计算成本。此外，边缘设备收集的数据涉及用户隐私，这一挑战可通过隐私保护的分布式范式——即联邦学习（FL）——成功应对。该框架允许边缘设备训练并交换模型，但同时也增加了通信开销。因此，为应对基于联邦学习的深度异常检测在通信、处理与存储方面日益增长的挑战，神经网络剪枝有望显著降低处理、存储及通信复杂度。基于此，本文在联邦学习范式的服务器端提出了一种新颖的基于压缩的优化问题，该方案融合接收的本地模型广播并执行剪枝，从而生成更紧凑的模型。在异常检测与缺失值插补任务上的实验表明，与集中式方案相比，所提出的联邦学习场景及基于压缩的方法能够实现高压缩率（超过$99.7\%$），且性能损失可忽略不计（低于$1.18\%$）。