cs.DCFeb 28, 2025

FedDyMem: Efficient Federated Learning with Dynamic Memory and Memory-Reduce for Unsupervised Image Anomaly Detection

Authors: Silin Chen, Andy Liu, Kangjian Di, Yichu Xu, Han-Jia Ye, Wenhan Luo, Ningmu Zou

Organizations: School of Integrated Circuits, Nanjing University, Suzhou, 215163, Jiangsu, China. · National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210023, Jiangsu, China. · School of Artificial Intelligence, Nanjing University, Nanjing, 210023, Jiangsu, China. · Hong Kong University of Science and Technology, Hong Kong. · 

Abstract

Unsupervised image anomaly detection (UAD) has become a critical process in industrial and medical applications, where models are trained on normal samples without requiring labeled anomalies. However, even normal images may contain sensitive product designs, manufacturing information, or institution-specific population characteristics, making centralized data collection difficult in practical deployments. Federated UAD provides a promising decentralized solution, but it remains challenging because clients use only normal training samples, their feature distributions remain highly heterogeneous within the same task, and communication should be efficient while limiting the exposure of sensitive client information. To address these challenges, we propose FedDyMem, an efficient federated learning method with dynamic memory and memory-reduce for unsupervised image anomaly detection. Instead of exchanging full model parameters, FedDyMem facilitates knowledge sharing between the clients and server through reduced dynamic memory banks. In the local clients, a memory generator and a metric loss are employed to improve the consistency of the feature distribution for normal samples, leveraging the local model to update the memory bank dynamically. For efficient communication and data privacy, a memory-reduce method based on weighted averages is proposed to significantly decrease the scale of memory banks. This representation reduces communication overhead and empirically lowers reconstruction fidelity under inversion attacks. On the server, global memory is constructed and distributed to individual clients through k-means aggregation. Experiments on six federated UAD tasks constructed from eleven public industrial and medical datasets show that FedDyMem consistently improves anomaly detection and localization while reducing communication cost.

Figures & tables

Explore similar work

CardsList
  1. Attention, Anomalies! Handling Attention Layers in Unsupervised Federated Outlier Detection

    Aug 5, 2026Mihailo Ilić, Miloš Savić, Vladimir Kurbalija +3Memory-Augmented Neural NetworksFederated Learning Aggregation

  2. Federated Coreset Subsampling for Distributed Memory Banks

    Oct 12, 2026Jason Witzemann, Daniel Pröll, Sebastian HegenbartMemory-Bank-Based Anomaly DetectionCoreset Selection

  3. FedUHD: Unsupervised Federated Learning using In-Memory Hyperdimensional Computing

    Aug 16, 2025You Hak Lee, Keming Fan, Xiaofan Yu +4Compute-in-MemoryFederated Learning Aggregation