Results 51 to 60 of about 31,140,578 (184)

The infectious intestinal disease study of England: a prospective evaluation of symptoms and health care use after an acute episode [PDF]

, 2003
The sequelae of Infectious Intestinal Disease (IID) in a population-based sample of cases and matched controls were investigated for a period of 3 months following the initial infection.
Rodrigues, L.C., Hudson, M.J., Cowden, JM, Wheeler, JG, Cumberland, P., Rodrigues, LC, Tompkins, D.S., Sethi, D., IID Study Executive, Hudson, MJ, Roderick, PJ, Tompkins, DS, Roderick, P.J., Roberts, JA, Wheeler, J.G., Roberts, J.A., Cumberland, P, Cowden, J.M., Sethi, D   +18 more
core   +1 more source

Linear Scalarization for Byzantine-robust learning on non-IID data

, 2022
In this work we study the problem of Byzantine-robust learning when data among clients is heterogeneous. We focus on poisoning attacks targeting the convergence of SGD.
Errami, Latifa, Bergou, El Houcine
core  

Non-IID Learning for Recommendation, Time Series and Hashing [PDF]

, 2023
University of Technology Sydney. Faculty of Engineering and Information Technology.For several decades, the independent and identically distributed (short for IID) assumption has laid the foundation of data learning, simplifying real-world data's ...
Zhang, Qi
core   +1 more source

Fed-TDA: Federated Tabular Data Augmentation on Non-IID Data

CoRR, 2022
Non-independent and identically distributed (non-IID) data is a key challenge in federated learning (FL), which usually hampers the optimization convergence and the performance of FL. Existing data augmentation methods based on federated generative models or raw data sharing strategies for solving the non-IID problem still suffer from low performance ...
Shaoming Duan, Chuanyi Liu, Peiyi Han, Tianyu He, Yifeng Xu, Qiyuan Deng   +5 more
openaire   +2 more sources

Mitigating non-IID data impact in federated learning with entropy

, 2023
Algoritmos de Machine Learning (ML) possibilitam processar um conjunto de dados de entradas para gerar coeficientes que ajustem a saída a um resultado previamente conhecido, como menor erro possível, fazendo com que seja possível reconhecer e extrair ...
Orlandi, Fernanda Cavalheiro
core   +1 more source

Federated Learning for Sentiment Analysis in Presence of Non-IID Data: Sensitivity of Deep Learning Models

IEEE Access
In sentiment analysis, data are commonly distributed across many devices, and traditional machine learning requires transferring these data to a central location exposing data to security and privacy risks. Federated Learning (FL) avoids this transfer by
Davoud Gholamiangonabadi, Katarina Grolinger   +1 more
doaj   +1 more source

A Distributed Privacy Preserved Federated Learning Approach for Revolutionizing Pneumonia Detection in Isolated Heterogenous Data Silos [PDF]

International Journal of Mathematical, Engineering and Management Sciences
Pneumonia is a respiratory lung contamination that ranges in severity from mild to lethal outcomes. The analysis of tomographic images is the most significant method of pneumonia detection.
Shagun Sharma, Kalpna Guleria
doaj   +1 more source

Privacy Protection in Prosumer Energy Management Based on Federated Learning

IEEE Access, 2021
With the booming development of prosumers, there is an urgent need for a prosumer energy management system to take full advantage of the flexibility of prosumers and take into account the interests of other parties.
Yunfeng Li, Xiaoling Li, Gangqiang Li, Zhitao Li   +3 more
doaj   +1 more source

Adaptive Federated Learning on Non-IID Data With Resource Constraint

, 2022
Federated learning (FL) has been widely recognized as a promising approach by enabling individual end-devices to cooperatively train a global model without exposing their own data.
Zhan, Yufeng, Zeng, Deze, Liu, Qifeng, Zhang, Jie, Guo, Song, Qu, Zhihao, Akerkar, Rajendra   +6 more
core   +1 more source

Overcoming Forgetting in Federated Learning on Non-IID Data

CoRR, 2019
We tackle the problem of Federated Learning in the non i.i.d. case, in which local models drift apart, inhibiting learning. Building on an analogy with Lifelong Learning, we adapt a solution for catastrophic forgetting to Federated Learning. We add a penalty term to the loss function, compelling all local models to converge to a shared optimum. We show
Neta Shoham, Tomer Avidor, Aviv Keren, Nadav Israel, Daniel Benditkis, Liron Mor-Yosef, Itai Zeitak   +6 more
openaire   +2 more sources