mlsanityData to 14 Oct 2026

Federated Attention Autoencoders with a Stochastic Aggregation Scheme for Anomaly Detection

arXiv 2608.08906 ↗First posted 9 Aug 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Outlier detection in decentralized data environments is a challenging task for many machine learning implementations, particularly in settings where data cannot be shared. Recently, there have been advances in federated outlier detection, some of which are based on the use of autoencoder networks. The introduction of attention mechanisms to autoencoders boosts their efficiency. However, the application of attention-based models in federated learning remains underdeveloped due to the absence of proper aggregation functions for these types of networks. In our work, we propose two novel aggregation functions tailored for attention-based autoencoders, which better preserve the learned information stored within the memory modules of these networks. We evaluated our approach on the KDDCUP10 dataset, and we showed that the proposed methods achieve up to 2.9% and 5.1% better results for F1 score and AUC ROC respectively when compared to traditional autoencoders.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 9 Aug 2026.

Builds on

27 of 45 references.

References · 27

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  5. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
  6. 2019Agnostic Federated Learningcited by 456
  7. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  8. 2014Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networkscited by 300
  9. 2020Federated Learning of a Mixture of Global and Local Modelscited by 210
  10. 2020Deep Learning for Anomaly Detection: A Reviewcited by 159
  11. 2019Federated Evaluation of On-device Personalizationcited by 147
  12. 2016Deep Structured Energy Based Models for Anomaly Detectioncited by 114
15 more
  1. 2021Distributionally Robust Federated Averagingcited by 104
  2. 2019Multi-task Self-Supervised Learning for Human Activity Detectioncited by 102
  3. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 99
  4. 2020Federated Unsupervised Representation Learningcited by 93
  5. 2018D"IoT: A Federated Self-learning Anomaly Detection System for IoTcited by 89
  6. 2013Submodular Optimization with Submodular Cover and Submodular Knapsack Constraintscited by 41
  7. 2019Abnormal Client Behavior Detection in Federated Learningcited by 40
  8. 2021Federated Learning for Malware Detection in IoT Devicescited by 36
  9. 2024Green Federated Learning: A new era of Green Aware AIcited by 12
  10. 2022Personalized Federated Learning via Convex Clusteringcited by 10
  11. 2022Fast Deep Autoencoder for Federated learningcited by 10
  12. 2021FedHybrid: A Hybrid Primal-Dual Algorithm Framework for Federated Optimizationcited by 7
  13. 2021Tax Evasion Risk Management Using a Hybrid Unsupervised Outlier Detection Methodcited by 3
  14. 2024FedAD-Bench: A Unified Benchmark for Federated Unsupervised Anomaly Detection in Tabular Datacited by 3
  15. 2021Deep Learning Anomaly Detection for Cellular IoT with Applications in Smart Logisticscited by 2

Built on by

Not cited yet.