Results 11 to 20 of about 31,140,529 (283)
Federated learning on non-IID data: A survey [PDF]
Neurocomputing, 2021 Federated learning is an emerging distributed machine learning framework for privacy preservation. However, models trained in federated learning usually have worse performance than those trained in the standard centralized learning mode, especially when the training data are not independent and identically distributed (Non-IID) on the local devices. In
Yaochu Jin, Hangyu Zhu
exaly +7 more sources
Detecting Outliers in Non-IID Data: A Systematic Literature Review
IEEE Access, 2023 Outlier detection (outlier and anomaly are used interchangeably in this review) in non-independent and identically distributed (non-IID) data refers to identifying unusual or unexpected observations in datasets that do not follow an independent and ...
Shafaq Siddiqi +3 more
doaj +4 more sources
Federated Learning With Taskonomy for Non-IID Data
IEEE Transactions on Neural Networks and Learning Systems, 2023 Classical federated learning approaches incur significant performance degradation in the presence of non-IID client data. A possible direction to address this issue is forming clusters of clients with roughly IID data. Most solutions following this direction are iterative and relatively slow, also prone to convergence issues in discovering underlying ...
Hadi Jamali-Rad, Anuj Singh
exaly +8 more sources
Homophily outlier detection in non-IID categorical data [PDF]
Data Mining and Knowledge Discovery, 2021 To appear in Data Ming and Knowledge Discovery ...
Guansong Pang +2 more
openaire +3 more sources
Cross-Domain Federated Data Modeling on Non-IID Data. [PDF]
Comput Intell Neurosci, 2022 Federated learning has received sustained attention in recent years for its distributed training model that fully satisfies the need for privacy concerns. However, under the nonindependent identical distribution, the data heterogeneity of different parties with different data patterns significantly degrades the prediction performance of the federated ...
Chai B, Liu K, Yang R.
europepmc +3 more sources
Federated Learning with Non-IID Data [PDF]
CoRR, 2018 Federated learning enables resource-constrained edge compute devices, such as mobile phones and IoT devices, to learn a shared model for prediction, while keeping the training data local. This decentralized approach to train models provides privacy, security, regulatory and economic benefits.
Yue Zhao 0041 +5 more
openaire +4 more sources
Client Selection for Federated Learning With Non-IID Data in Mobile Edge Computing
IEEE Access, 2021 Federated Learning (FL) has recently attracted considerable attention in internet of things, due to its capability of enabling mobile clients to collaboratively learn a global prediction model without sharing their privacy-sensitive data to the server ...
Weiwei Wu, Weiwei Wu, Xiumin Wang
exaly +3 more sources
Privacy-Enhanced Federated Learning for Non-IID Data
Mathematics, 2023 Federated learning (FL) allows the collaborative training of a collective model by a vast number of decentralized clients while ensuring that these clients’ data remain private and are not shared. In practical situations, the training data utilized in FL
Shuhui Wu
exaly +3 more sources
Secure and decentralized federated learning framework with non-IID data based on blockchain [PDF]
HeliyonFederated learning enables the collaborative training of machine learning models across multiple organizations, eliminating the need for sharing sensitive data.
Feng Zhang +3 more
doaj +2 more sources
Peer-to-Peer Learning+Consensus with Non-IID Data
2023 57th Asilomar Conference on Signals, Systems, and Computers, 2023 Peer-to-peer deep learning algorithms are enabling distributed edge devices to collaboratively train deep neural networks without exchanging raw training data or relying on a central server. Peer-to-Peer Learning (P2PL) and other algorithms based on Distributed Local-Update Stochastic/mini-batch Gradient Descent (local DSGD) rely on interleaving epochs
Srinivasa Pranav, José M. F. Moura
openaire +3 more sources