AN ON-DEVICE FEDERATED LEARNING APPROACH FOR COOPERATIVE ANOMALY DETECTION
Rei Ito, Mineto Tsukada, Hiroki Matsutani · 2020
Most edge AI focuses on prediction tasks on resource-limited edge devices, while the training is done at server machines, so retraining a model on the edge devices to reflect environmental changes is a complicated task. To follow such a concept drift, a neural-network based on-device learning approach is recently proposed, so that edge devices train incoming data at runtime to update their model. In this case, since a training is done at distributed edge devices, the issue is that only a limited amount of training data can be used for each edge device. To address this issue, one approach is a cooperative learning or federated learning, where edge devices exchange their trained results and update their model by using those collected from the other devices. In this paper, as an on-device learning algorithm, we focus on OS-ELM (Online Sequential Extreme Learning Machine) and combine it with autoencoder for anomaly detection. We extend it for an on-device federated learning so that edge devices can exchange their trained results and update their model by using those collected from the other edge devices. Evaluation results using a driving dataset of cars and a human activity dataset demonstrate that the proposed on-device federated learning can produce a merged model by combining trained results from multiple edge devices as accurately as a conventional backpropagation based neural network. Latency for the merging is reasonable, and it can merge the models faster than continuously executing the sequential learning.