Results 61 to 70 of about 12,973 (156)

Communication Efficiency and Non-Independent and Identically Distributed Data Challenge in Federated Learning: A Systematic Mapping Study

Applied Sciences
Federated learning has emerged as a promising approach for collaborative model training across distributed devices. Federated learning faces challenges such as Non-Independent and Identically Distributed (non-IID) data and communication challenges.
Basmah Alotaibi, Fakhri Alam Khan, Sajjad Mahmood   +2 more
doaj   +1 more source

KL-FedDis: A federated learning approach with distribution information sharing using Kullback-Leibler divergence for non-IID data

Neuroscience Informatics
Data Heterogeneity or Non-IID (non-independent and identically distributed) data identification is one of the prominent challenges in Federated Learning (FL).
Md. Rahad, Ruhan Shabab, Mohd. Sultan Ahammad, Md. Mahfuz Reza, Amit Karmaker, Md. Abir Hossain   +5 more
doaj   +1 more source

Pretraining Client Selection Algorithm Based on a Data Distribution Evaluation Model in Federated Learning

IEEE Access
Federated Learning (FL) allows task initiators (servers) to utilize data from task participants (clients) to train machine learning models while protecting data privacy.
Chang Xu, Hong Liu, Kexin Li, Wanglei Feng, Wei Qi   +4 more
doaj   +1 more source

Mitigating Backdoor Attacks in Federated Learning Systems Under Non‑IID Data: A Comprehensive Survey

IJCI International Journal of Computers and Information
Federated Learning (FL) enables collaborative model training while preserving data privacy, but its decentralized nature exposes it to backdoor attacks, where malicious clients inject poisoned updates that embed hidden triggers into the global model ...
Ahmed Soliman, Khalid Amin, Noura Semary, Hayam Mousa   +3 more
doaj   +1 more source

Analysis and Improvement of Entropy Estimators in NIST SP 800-90B for Non-IID Entropy Sources

IACR Transactions on Symmetric Cryptology, 2017
Random number generators (RNGs) are essential for cryptographic applications. In most practical applications, the randomness of RNGs is provided by entropy sources.
Shuangyi Zhu, Yuan Ma, Tianyu Chen, Jingqiang Lin, Jiwu Jing   +4 more
doaj   +1 more source

Cloud–Edge–End Collaborative Federated Learning: Enhancing Model Accuracy and Privacy in Non-IID Environments

Sensors
Cloud–edge–end computing architecture is crucial for large-scale edge data processing and analysis. However, the diversity of terminal nodes and task complexity in this architecture often result in non-independent and identically distributed (non-IID ...
Ling Li, Lidong Zhu, Weibang Li
doaj   +1 more source

Addressing Non-IID with Data Quantity Skew in Federated Learning

Information
Non-IID is one of the key challenges in federated learning. Data heterogeneity may lead to slower convergence, reduced accuracy, and more training rounds.
Narisu Cha, Long Chang
doaj   +1 more source

CHPFL: Clustered adaptive hierarchical federated learning for edge-level personalization

High-Confidence Computing
Federated learning faces challenges with non-IID data distributions, often resulting in suboptimal performance for individual clients with the global model. To address this issue, we propose a clustered hierarchical personalized federated learning (CHPFL)
Lihua Song, Jing Li, Honglu Jiang, Shuhua Wei, Yufei Guo   +4 more
doaj   +1 more source

DAG-Based Blockchain Sharding for Secure Federated Learning with Non-IID Data. [PDF]

Sensors (Basel), 2022
Lee J, Kim W.
europepmc   +1 more source

Edge-Federated Learning-Based Intelligent Intrusion Detection System for Heterogeneous Internet of Things

IEEE Access
Distributed denial of service (DDoS) is an awful cyber threat, becoming more prevalent with mature heterogeneous IoT (HetIoT) applications like intelligent agriculture, wearables, and self-driving cars. Developing intelligent intrusion detection systems (
Shalaka S. Mahadik, Pranav M. Pawar, Raja Muthalagu   +2 more
doaj   +1 more source