Results 11 to 20 of about 10,022,386 (288)

Federated Learning with Non-IID Data [PDF]

CoRR, 2022
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.
Suda, Naveen, Zhao, Yue, Chandra, Vikas, Lai, Liangzhen, Li, Meng, Civin, Damon   +5 more
core   +4 more sources

Federated User Clustering for non-IID Federated Learning [PDF]

Electron. Commun. Eur. Assoc. Softw. Sci. Technol., 2021
Federated Learning (FL) is one of the leading learning paradigms for enabling a more significant presence of intelligent applications in networking considering highly distributed environments while preserving user privacy.
Cerqueira, Eduardo, Braun, Torsten, Pacheco, Lucas, Cerqueira, Eduadro, Rosário, Denis, Pacheco, Lucas de Sousa   +5 more
core   +3 more sources

Beyond i.i.d.: Non-IID Thinking, Informatics, and Learning

IEEE Intelligent Systems, 2023
In science, technology, engineering, and their applications, a ubiquitous assumption is independent and identically distributed (i.i.d. or IID).
Cao, L
core   +3 more sources

Shallow and Deep Non-IID Learning on Complex Data

Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023
Non-IID (i.i.d.) data holds complex non-IIDness, e.g., couplings and interactions (non-independent) and heterogeneities (not IID drawn from a given distribution).
Yu, PS, Zhao, Z, Cao, LL
core   +3 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.
Pranav, Srinivasa, Moura, José M. F.
core   +3 more sources

ProFed: A Benchmark for Proximity-Based Non-IID Federated Learning

Journal of Open Research Software
Federated Learning (FL) has emerged as a key paradigm in machine learning but its performance often deteriorates under non-independent and identically distributed (non-IID) client data.
Davide Domini, Christian Otte Ingemann, Gianluca Aguzzi, Lukas Esterle, Mirko Viroli   +4 more
doaj   +2 more sources

Coupled Matrix Factorization Within Non-IID Context [PDF]

, 2015
© Springer International Publishing Switzerland 2015. Recommender systems research has experienced different stages such as from user preference understanding to content analysis.
Longbing Cao, Fangfang Li, Cao, L, Guandong Xu, Li, F, Xu, G   +5 more
core   +4 more sources

Distribution-Regularized Federated Learning on Non-IID Data

2023 IEEE 39th International Conference on Data Engineering (ICDE), 2023
Federated learning (FL) has emerged as a popular machine learning paradigm recently. Compared with traditional distributed learning, its unique challenges mainly lie in communication efficiency and non-IID (heterogeneous data) problem.
Wang, Yansheng, Zhou, Zimu, Tong, Yongxin, Pan, Sinno Jialin, Zhang, Ruisheng, Yang, Qiang, Fan, Lixin   +6 more
core   +2 more sources

Federated multimodal malware classification under non-IID data

Cybersecurity
Malware data in real-world cybersecurity applications are typically distributed across multiple organizations, and privacy, security, and compliance constraints prevent these data from being shared with a central server.
Shaohua Liu, Wenbo Zhang, Tingting Yang, Guanghao Li, Lihua Zhang   +4 more
doaj   +2 more sources

Federated XGBoost on Sample-Wise Non-IID Data

CoRR, 2022
Federated Learning (FL) is a paradigm for jointly training machine learning algorithms in a decentralized manner which allows for parties to communicate with an aggregator to create and train a model, without exposing the underlying raw data distribution
Jones, Katelinh, Baracaldo, Nathalie, Zhou, Yi, Ong, Yuya Jeremy   +3 more
core   +3 more sources