Results 281 to 290 of about 9,950,038 (297)
Some of the next articles are maybe not open access.
Non-IID federated learning with Mixed-Data Calibration
Applied and Computational EngineeringFederated learning (FL) is a privacy-preserving and collaborative machine learning approach for decentralized data across multiple clients. However, the presence of non-independent and non-identically distributed (non-IID) data among clients poses challenges to the performance of the global model.
Xufei Zhang, Yiqing Shen
openaire +1 more source
Reschedule Gradients: Temporal Non-IID Resilient Federated Learning
IEEE Internet of Things Journal, 2023Xianyao You +4 more
openaire +1 more source
FedAgent: Federated Learning on Non-IID Data via Reinforcement Learning and Knowledge Distillation
Expert systems with applicationsBingli Sun +3 more
semanticscholar +1 more source
Beyond i.i.d.: Non-IID Thinking, Informatics, and Learning
IEEE Intelligent Systems, 2022openaire +1 more source
Discrepancy-Aware Federated Learning for Non-IID Data
2023 IEEE Wireless Communications and Networking Conference (WCNC), 2023Jianhua Shen, Siguang Chen
openaire +1 more source
Kernel Measures of Independence for Non-IID Data
2009Many machine learning algorithms can be formulated in the framework of statistical independence such as the Hilbert Schmidt Independence Criterion. In this paper, we extend this criterion to deal with structured and interdependent observations. This is achieved by modeling the structures using undirected graphical models and comparing the Hilbert space
Zhang, X. +3 more
openaire +1 more source
Non-IID Distributed Learning with Optimal Mixture Weights
2023Jian Li +3 more
openaire +1 more source