English

Online Continual Learning for Anomaly Detection in IoT under Data Distribution Shifts

Machine Learning 2026-03-10 v1

Abstract

In this work, we present OCLADS, a novel communication framework with continual learning (CL) for Internet of Things (IoT) anomaly detection (AD) when operating in non-stationary environments. As the statistical properties of the observed data change with time, the on-device inference model becomes obsolete, which necessitates strategic model updating. OCLADS keeps track of data distribution shifts to timely update the on-device IoT AD model. To do so, OCLADS introduces two mechanisms during the interaction between the resource-constrained IoT device and an edge server (ES): i) an intelligent sample selection mechanism at the device for data transmission, and ii) a distribution-shift detection mechanism at the ES for model updating. Experimental results with TinyML demonstrate that our proposed framework achieves high inference accuracy while realizing a significantly smaller number of model updates compared to the baseline schemes.

Keywords

Cite

@article{arxiv.2603.07507,
  title  = {Online Continual Learning for Anomaly Detection in IoT under Data Distribution Shifts},
  author = {Matea Marinova and Shashi Raj Pandey and Junya Shiraishi and Martin Voigt Vejling and Valentin Rakovic and Petar Popovski},
  journal= {arXiv preprint arXiv:2603.07507},
  year   = {2026}
}

Comments

Manuscript submitted to EUSIPCO 2026. The copyright might be transferred without further notice

R2 v1 2026-07-01T11:08:58.193Z