# FLARE: Detection and Mitigation of Concept Drift for Federated Learning based IoT Deployments

arXiv: https://arxiv.org/abs/2305.08504 · HTML: https://mlsanity.com/paper/2305.08504/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 15 May 2023.

## Builds on (most cited first, 6 of 6)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [MNIST-C: A Robustness Benchmark for Computer Vision](https://mlsanity.com/paper/1906.02337/) (2019)
- [Characterizing Concept Drift](https://mlsanity.com/paper/1511.03816/) (2015)
- [Demo: LE3D: A Privacy-preserving Lightweight Data Drift Detection Framework](https://mlsanity.com/paper/2211.01827/) (2022)
- [LE3D: A Lightweight Ensemble Framework of Data Drift Detectors for Resource-Constrained Devices](https://mlsanity.com/paper/2211.01840/) (2022)

## Built on by (most cited first, 2 of 2)

- [Federated Continual Learning: Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2502.07059/) (2025)
- [FLAME: Adaptive and Reactive Concept Drift Mitigation for Federated Learning Deployments](https://mlsanity.com/paper/2410.01386/) (2024)

## Abstract (arXiv)

Intelligent, large-scale IoT ecosystems have become possible due to recent advancements in sensing technologies, distributed learning, and low-power inference in embedded devices. In traditional cloud-centric approaches, raw data is transmitted to a central server for training and inference purposes. On the other hand, Federated Learning migrates both tasks closer to the edge nodes and endpoints. This allows for a significant reduction in data exchange while preserving the privacy of users. Trained models, though, may under-perform in dynamic environments due to changes in the data distribution, affecting the model's ability to infer accurately; this is referred to as concept drift. Such drift may also be adversarial in nature. Therefore, it is of paramount importance to detect such behaviours promptly. In order to simultaneously reduce communication traffic and maintain the integrity of inference models, we introduce FLARE, a novel lightweight dual-scheduler FL framework that conditionally transfers training data, and deploys models between edge and sensor endpoints based on observing the model's training behaviour and inference statistics, respectively. We show that FLARE can significantly reduce the amount of data exchanged between edge and sensor nodes compared to fixed-interval scheduling methods (over 5x reduction), is easily scalable to larger systems, and can successfully detect concept drift reactively with at least a 16x reduction in latency.