Benchmarking Federated Learning Under Realistic Non-IID Conditions: A Structured Partitioning Approach Using ImageNet
Abstract
See publication for more information.
Type
Publication
Benchmarking Federated Learning Under Realistic Non-IID Conditions: A Structured Partitioning Approach Using ImageNet
Citation: T. Legler, V. Hegiste, M. Ruskowski. “Benchmarking Federated Learning Under Realistic Non-IID Conditions: A Structured Partitioning Approach Using ImageNet.” In: Proceedings of the 2025 IEEE 45th International Conference on Distributed Computing Systems Workshops (ICDCSW). IEEE, 2025, pp. —. DOI: 10.1109/ICDCSW63273.2025.00137.
MSc. Tatjana Legler
Researcher
Tatjana Legler studied mechanical engineering at the Technical University of Kaiserslautern. She wrote her master thesis on “Optimization of automated visual inspection of common rails using neural networks”. She has been working as a research assistent at the Chair of Machine Tools and Control Systems since November 2017.
Prof. Dr.-Ing. Martin Ruskowski
Head of Chair Department of Machine Tools and Control Systems (WSKL)
add info