This study aims to propose novel edge device-tailored federated learning algorithms of local classifiers (stochastic gradient descent, support vector machines), namely, FL-lSGD and FL-lSVM. These algorithms are designed to address the challenge of large-scale ImageNet classification.
Design/methodology/approach
The authors’ FL-lSGD and FL-lSVM trains in a parallel and incremental manner to build an ensemble local classifier on Raspberry Pis without requiring data exchange. The algorithms load small data blocks of the local training subset stored on the Raspberry Pi sequentially to train the local classifiers. The data block is split into k partitions using the k-means algorithm, and models are trained in parallel on each data partition to enable local data classification.
Findings
Empirical test results on the ImageNet data set show that the authors’ FL-lSGD and FL-lSVM algorithms with 4 Raspberry Pis (Quad core Cortex-A72, ARM v8, 64-bit SoC @ 1.5GHz, 4GB RAM) are faster than the state-of-the-art LIBLINEAR algorithm run on a PC (Intel(R) Core i7-4790 CPU, 3.6 GHz, 4 cores, 32GB RAM).
Originality/value
Efficiently addressing the challenge of large-scale ImageNet classification, the authors’ novel federated learning algorithms of local classifiers have been tailored to work on the Raspberry Pi. These algorithms can handle 1,281,167 images and 1,000 classes effectively.
Tạp chí khoa học Trường Đại học Cần Thơ
Lầu 4, Nhà Điều Hành, Khu II, đường 3/2, P. Xuân Khánh, Q. Ninh Kiều, TP. Cần Thơ
Điện thoại: (0292) 3 872 157; Email: tapchidhct@ctu.edu.vn
Chương trình chạy tốt nhất trên trình duyệt IE 9+ & FF 16+, độ phân giải màn hình 1024x768 trở lên
