Recent Advances in Federated Learning Algorithms
A special issue of Algorithms (ISSN 1999-4893). This special issue belongs to the section "Evolutionary Algorithms and Machine Learning".
Deadline for manuscript submissions: closed (29 February 2024) | Viewed by 613
Special Issue Editors
Interests: federated learning; applied machine learning; sensor data analytics
Interests: wireless communications and networking; mobile edge computing and edge AI; federated and distributed learning; Internet-of-Things and smart city
Special Issue Information
Dear Colleagues,
Federated learning (FL) has emerged as a promising approach to address the limitations of traditional centralized machine learning algorithms. By training models collaboratively on decentralized devices, FL enables privacy preservation and distributed learning without compromising data security. Since its inception in 2017, FL algorithms have gained significant attention due to their applications in various domains, including the Internet of Things (IoT), healthcare, natural language processing, computer vision, and many others. To foster open collaboration among co-creators of FL and promote widespread adoption of this paradigm, it is imperative for communities of data owners to autonomously organize themselves during FL model training. To deploy FL into the wild, there is an utmost need for robust and fair aggregation algorithms to support the server. These algorithms must encompass various aspects such as security and robustness, privacy preservation, fairness, and establishment of edge computing methods. By exploring these aspects, data owners can actively engage in open and dynamic collaboration within the FL frameworks. This Special Issue aims to bring together researchers, practitioners, and industry experts from around the world to explore the latest advancements, deployment challenges, and opportunities in the field of FL.
We invite researchers and practitioners to submit original research papers on the following topics related to federated learning (but not limited to):
- Federated learning frameworks;
- Privacy-preserving machine learning algorithms;
- Adversarial attacks on distributed learning paradigms;
- Algorithms to defend against data poisoning and backdoor attacks;
- Gradient leakage vulnerabilities in federated learning;
- Performance fairness across clients under federated learning algorithms;
- Privacy and security in federated learning;
- Federated learning for edge computing and IoT;
- Real-world applications and case studies of federated learning;
- Federated learning algorithms for handling data imbalance issues both locally and globally on clients and server, respectively;
- Federated learning algorithms to address client selection using replacement and without replacement techniques;
- Integrating knowledge distillation in federated learning algorithms.
Dr. Ashish Gupta
Dr. Yuyi Mao
Guest Editors
Dr. Rahul Mishra
Guest Editor Assistant
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Algorithms is an international peer-reviewed open access monthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
