Results 71 to 80 of about 12,973 (156)

Adversarially-Regularized Mixed Effects Deep Learning (ARMED) Models Improve Interpretability, Performance, and Generalization on Clustered (non-iid) Data. [PDF]

IEEE Trans Pattern Anal Mach Intell, 2023
Nguyen KP, Treacher AH, Montillo AA.
europepmc   +1 more source

Advanced Optimization Techniques for Federated Learning on Non-IID Data

Future Internet
Federated learning enables model training on multiple clients locally, without the need to transfer their data to a central server, thus ensuring data privacy.
Filippos Efthymiadis, Aristeidis Karras, Christos Karras, Spyros Sioutas   +3 more
doaj   +1 more source

VINO_EffiFedAV: VINO with efficient federated learning through selective client updates for real-time autonomous vehicle object detection

Results in Engineering
The advancement of autonomous vehicle technology relies heavily on sophisticated machine-learning models that facilitate real-time object detection and classification.
K. Vinoth, P. Sasikumar
doaj   +1 more source

Global Convergence of Continual Learning on Non-IID Data

CoRR
Continual learning, which aims to learn multiple tasks sequentially, has gained extensive attention. However, most existing work focuses on empirical studies, and the theoretical aspect remains under-explored. Recently, a few investigations have considered the theory of continual learning only for linear regressions, establishes the results based on ...
Fei Zhu 0004, Yujing Liu, Wenzhuo Liu, Zhaoxiang Zhang 0001   +3 more
openaire   +2 more sources

Federated Learning for Breast Cancer Classification: A Comparative Study of Aggregation Methods

Information
Federated Learning (FL) allows healthcare institutions to collaboratively develop machine learning models while safeguarding patient data, making it ideal for privacy-sensitive medical imaging.
Nadjat Saàdia Lachemi, Medjeded Merati, Saïd Mahmoudi   +2 more
doaj   +1 more source

Fairness amidst non‐IID graph data: A literature review

AI Magazine
AbstractThe growing importance of understanding and addressing algorithmic bias in artificial intelligence (AI) has led to a surge in research on AI fairness, which often assumes that the underlying data are independent and identically distributed (IID).
Wenbin Zhang 0002, Jeremy C. Weiss, Shuigeng Zhou, Toby Walsh   +3 more
openaire   +2 more sources

A thorough assessment of the non-IID data impact in federated learning

Journal of Industrial Information Integration
Federated learning (FL) allows collaborative machine learning (ML) model training among decentralized clients' information, ensuring data privacy. The decentralized nature of FL deals with non-independent and identically distributed (non-IID) data. This open problem has notable consequences, such as decreased model performance and more significant ...
Daniel Mauricio Jimenez Gutierrez, Mehrdad Hassanzadeh, Aris Anagnostopoulos, Ioannis Chatzigiannakis, Andrea Vitaletti   +4 more
openaire   +2 more sources

FedDB: A Federated Learning Approach Using DBSCAN for DDoS Attack Detection

Applied Sciences
The rise of Distributed Denial of Service (DDoS) attacks on the internet has necessitated the development of robust and efficient detection mechanisms. DDoS attacks continue to present a significant threat, making it imperative to find efficient ways to ...
Yi-Chen Lee, Wei-Che Chien, Yao-Chung Chang   +2 more
doaj   +1 more source

Differentially Private Federated Clustering Over Non-IID Data

IEEE Internet of Things Journal
34 pages, 4 figures, 1 ...
Yiwei Li 0003, Shuai Wang 0033, Chong-Yung Chi, Tony Q. S. Quek   +3 more
openaire   +2 more sources

Comparative Analysis of Centralized and Federated Intrusion Detection in IoT-Enabled Cyber-Physical Systems Under Data and Label-Skew

IEEE Access
Cyber-Physical Systems (CPS) increasingly leverage Internet of Things (IoT) technologies to enable seamless communication and control across distributed devices.
Muhammad Ali Khan, Rao Naveed Bin Rais, Osman Khalid, Mohamed Deriche   +3 more
doaj   +1 more source