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

TL;DR

This paper introduces OCLADS, a continual learning framework for IoT anomaly detection that adapts to data distribution shifts, improving accuracy and reducing model updates in resource-constrained environments.

Contribution

The paper proposes a novel communication framework with mechanisms for data selection and distribution-shift detection to enhance IoT anomaly detection under non-stationary data conditions.

Findings

High inference accuracy achieved in experiments.

Significantly fewer model updates compared to baselines.

Effective detection of data distribution shifts.

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.