Results 1 to 10 of about 129,870 (304)

Multi-Objective Evolutionary Federated Learning [PDF]

IEEE Transactions on Neural Networks and Learning Systems, 2020
Federated learning is an emerging technique used to prevent the leakage of private information. Unlike centralized learning that needs to collect data from users and store them collectively on a cloud server, federated learning makes it possible to learn a global model while the data are distributed on the users' devices.
Zhu, Hangyu, Jin, Yaochu
openaire   +4 more sources

Benchmark for Personalized Federated Learning

IEEE Open Journal of the Computer Society
Federated learning is a distributed machine learning approach that allows a single server to collaboratively build machine learning models with multiple clients without sharing datasets.
Koji Matsuda, Yuya Sasaki, Chuan Xiao, Makoto Onizuka   +3 more
doaj   +1 more source

Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data

, 2023
On-device machine learning (ML) enables the training process to exploit a massive amount of user-generated private data samples. To enjoy this benefit, inter-device communication overhead should be minimized.
Bennis, Mehdi, Jeong, Eunjeong, Kim, Hyesung, Kim, Seong-Lyun, Oh, Seungeun, Park, Jihong   +5 more
core  

Advancements of Federated Learning Towards Privacy Preservation: From Federated Learning to Split Learning [PDF]

, 2021
Authors' preprint version (before any peer-review) of a book chapter to appear in the Book series "Studies in Computational Intelligence", Book title "Federated Learning Systems: Towards Next-generation AI", Book eds. Muhammad Habib ur Rehman and Mohamed Medhat Gaber, Publisher "Springer Nature Switzerland AG Gewerbestrasse 11, 6330 Cham, Switzerland."
Thapa, Chandra, Chamikara, M. A. P., Camtepe, Seyit A.   +2 more
openaire   +2 more sources

Learning domain-heterogeneous speaker recognition systems with personalized continual federated learning

EURASIP Journal on Audio, Speech, and Music Processing, 2023
Speaker recognition, the process of automatically identifying a speaker based on individual characteristics in speech signals, presents significant challenges when addressing heterogeneous-domain conditions.
Zhiyong Chen, Shugong Xu
doaj   +1 more source

The GLASS project: supporting secure shibboleth-based single sign-on to campus resources [PDF]

, 2007
Higher and Further education institutions in the UK are in the process of migrating their IT infrastructures to exploit Shibboleth technologies for federated access management. Ease of use and secure access are paramount to the successful uptake of these
Jiang, J., Sinnott, R.O., Watt, J.
core   +2 more sources

Research on federated learning approach based on local differential privacy

Tongxin xuebao, 2022
As a type of collaborative machine learning framework, federated learning is capable of preserving private data from participants while training the data into useful models.Nevertheless, from a viewpoint of information theory, it is still vulnerable for ...
Haiyan KANG, Yuanrui JI
doaj   +2 more sources

Meta-federated learning

Due to its distributed methodology alongside its privacy-preserving features, Federated Learning (FL) is vulnerable to training time adversarial attacks. In this study, our focus is on backdoor attacks in which the adversary's goal is to cause targeted misclassifications for inputs embedded with an adversarial trigger while maintaining an acceptable ...
Aramoon, Omid, Chen, Pin-Yu, Qu, Gang, Tian, Yuan   +3 more
openaire   +2 more sources

Dynamic Asynchronous Anti Poisoning Federated Deep Learning with Blockchain-Based Reputation-Aware Solutions

Sensors, 2022
As promising privacy-preserving machine learning technology, federated learning enables multiple clients to train the joint global model via sharing model parameters.
Zunming Chen, Hongyan Cui, Ensen Wu, Xi Yu   +3 more
doaj   +1 more source

A dynamic incentive and reputation mechanism for energy-efficient federated learning in 6G

Digital Communications and Networks, 2023
As 5G becomes commercial, researchers have turned attention toward the Sixth-Generation (6G) network with the vision of connecting intelligence in a green energy-efficient manner.
Ye Zhu, Zhiqiang Liu, Peng Wang, Chenglie Du   +3 more
doaj   +1 more source