Results 11 to 20 of about 34,864,804 (179)

Fast converging Federated Learning with Non-IID Data

2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring), 2023
With the advancement of device capabilities, Internet of Things (IoT) devices can employ built-in hardware to perform machine learning (ML) tasks, extending their horizons in many promising directions. In traditional ML, data are sent to a server for training. However, this approach raises user privacy concerns.
Sigg Stephan, Naas Si Ahmed
openaire   +3 more sources

FedProc: Prototypical Contrastive Federated Learning on Non-IID data [PDF]

Future Generation Computer Systems, 2021
Federated learning allows multiple clients to collaborate to train high-performance deep learning models while keeping the training data locally. However, when the local data of all clients are not independent and identically distributed (i.e., non-IID),
Xu-Tong Mu, Yu-Long Shen, Ke Cheng, Xueli Geng, Jia-Xuan Fu, Tao Zhang, Zhiwei Zhang   +6 more
semanticscholar   +3 more sources

Entropy to Mitigate Non-IID Data Problem on Federated Learning for the Edge Intelligence Environment

IEEE Access, 2023
Machine Learning (ML) algorithms process input data making it possible to recognize and extract patterns from a large data volume. Likewise, Internet of Things (IoT) devices provide knowledge in a Federated Learning (FL) environment, sharing parameters ...
Fernanda C. Orlandi, Julio C. S. Dos Anjos, Valderi R. Q. Leithardt, Juan Francisco De Paz Santana, Claudio F. R. Geyer   +4 more
doaj   +2 more sources

Entropy-Regularized Federated Optimization for Non-IID Data

Algorithms
Federated learning (FL) struggles under non-IID client data when local models drift toward conflicting optima, impairing global convergence and performance.
Koffka Khan
doaj   +2 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

Non-IID Recommender Systems: A Review and Framework of Recommendation Paradigm Shifting

Engineering, 2016
While recommendation plays an increasingly critical role in our living, study, work, and entertainment, the recommendations we receive are often for irrelevant, duplicate, or uninteresting products and services.
Longbing Cao
exaly   +3 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

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.
Yansheng Wang, Yongxin Tong, Zimu Zhou, Ruisheng Zhang, Sinno Jialin Pan, Lixin Fan, Qiang Yang 0001   +6 more
openaire   +2 more sources

Federated Learning Architecture for Non-IID Data [PDF]

Jisuanji gongcheng, 2023
In the scenarios of federated learning involving ultra-large-scale edge devices, the local data of participants are non-Independent Identically Distribution(non-IID) pattern, resulting in an imbalance in overall training data and difficulty in defending ...
Tianchen QIU, Xiaoying ZHENG, Yongxin ZHU, Songlin FENG
doaj   +1 more source

Federated Learning on Non-IID Data Silos: An Experimental Study [PDF]

IEEE International Conference on Data Engineering, 2021
Due to the increasing privacy concerns and data regulations, training data have been increasingly fragmented, forming distributed databases of multiple “data silos” (e.g., within different organizations and countries).
Q. Li, Yi-Qun Diao, Quan Chen, Bing-Sheng He   +3 more
semanticscholar   +1 more source