Results 11 to 20 of about 6,308,360 (314)

Accelerating Fair Federated Learning: Adaptive Federated Adam

IEEE Transactions on Machine Learning in Communications and Networking
Federated learning is a distributed and privacy-preserving approach to train a statistical model collaboratively from decentralized data held by different parties. However, when the datasets are not independent and identically distributed, models trained
Li Ju, Tianru Zhang, Salman Toor, Andreas Hellander   +3 more
doaj   +2 more sources

Vulnerabilities in Federated Learning [PDF]

IEEE Access, 2021
With more regulations tackling the protection of users’ privacy-sensitive data in recent years, access to such data has become increasingly restricted. A new decentralized training paradigm, known as Federated Learning (FL), enables multiple clients located at different geographical locations to learn a machine learning model collaboratively ...
Nader Bouacida, Prasant Mohapatra
openaire   +3 more sources

Learning to Backdoor Federated Learning

CoRR, 2023
In a federated learning (FL) system, malicious participants can easily embed backdoors into the aggregated model while maintaining the model's performance on the main task. To this end, various defenses, including training stage aggregation-based defenses and post-training mitigation defenses, have been proposed recently.
Henger Li, Chen Wu, Sencun Zhu, Zizhan Zheng   +3 more
openaire   +3 more sources

A Survey of Federated Evaluation in Federated Learning

Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023
In traditional machine learning, it is trivial to conduct model evaluation since all data samples are managed centrally by a server. However, model evaluation becomes a challenging problem in federated learning (FL), which is called federated evaluation in this work.
Behnaz Soltani, Yipeng Zhou, Venus Haghighi, John C. S. Lui   +3 more
openaire   +3 more sources

Sustainable Federated Learning

CoRR, 2021
Potential environmental impact of machine learning by large-scale wireless networks is a major challenge for the sustainability of future smart ecosystems. In this paper, we introduce sustainable machine learning in federated learning settings, using rechargeable devices that can collect energy from the ambient environment.
Basak Guler, Aylin Yener
openaire   +2 more sources

Initiating the learning process: A model for federated searching and information literacy [PDF]

, 2007
Access to federated search tools is increasing and many academic libraries are now looking beyond implementation, and are considering the broader implications of federated searching such as its impact on information literacy programs.
Labelle, Patrick R.
core   +2 more sources

Incentivizing Federated Learning

CoRR, 2022
Federated Learning is an emerging distributed collaborative learning paradigm used by many of applications nowadays. The effectiveness of federated learning relies on clients' collective efforts and their willingness to contribute local data. However, due to privacy concerns and the costs of data collection and model training, clients may not always ...
Shuyu Kong, You Li 0008, Hai Zhou 0001
openaire   +2 more sources

Anarchic Federated Learning

CoRR, 2021
Present-day federated learning (FL) systems deployed over edge networks consists of a large number of workers with high degrees of heterogeneity in data and/or computing capabilities, which call for flexible worker participation in terms of timing, effort, data heterogeneity, etc. To satisfy the need for flexible worker participation, we consider a new
Haibo Yang 0001, Xin Zhang 0054, Prashant Khanduri, Jia Liu 0002   +3 more
openaire   +3 more sources

Dynamic Federated Learning [PDF]

2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2020
Federated learning has emerged as an umbrella term for centralized coordination strategies in multi-agent environments. While many federated learning architectures process data in an online manner, and are hence adaptive by nature, most performance analyses assume static optimization problems and offer no guarantees in the presence of drifts in the ...
Elsa Rizk, Stefan Vlaski, Ali H. Sayed
openaire   +4 more sources

Green Federated Learning

CoRR, 2023
The rapid progress of AI is fueled by increasingly large and computationally intensive machine learning models and datasets. As a consequence, the amount of compute used in training state-of-the-art models is exponentially increasing (doubling every 10 months between 2015 and 2022), resulting in a large carbon footprint.
Ashkan Yousefpour, Shen Guo, Ashish Shenoy, Sayan Ghosh, Pierre Stock, Kiwan Maeng, Schalk-Willem Krüger, Michael G. Rabbat, Carole-Jean Wu, Ilya Mironov   +9 more
openaire   +2 more sources