The "Special Session on Federated Learning on Big Data" aims to bring together researchers, industry practitioners, and policymakers to explore cutting-edge advancements and address pressing challenges in the application of federated learning to Big Data. Federated learning is revolutionizing the way organizations handle machine learning across distributed data sources, enabling collaborative model training without compromising data privacy. With the proliferation of data from various sources such as healthcare, finance, IoT, and multimedia, this session provides an invaluable opportunity to delve into the practical and theoretical aspects of federated learning, focusing on its integration with the 5Vs of Big Data: Volume, Velocity, Variety, Value, and Veracity.

The session will highlight recent innovations in federated learning algorithms and frameworks designed to handle the unique challenges posed by Big Data, such as heterogeneous data distributions and resource constraints. Furthermore, it will explore the interplay between federated learning and privacy-preserving mechanisms, ensuring secure data exchange across institutions and organizations. Special emphasis will be placed on real-world applications in healthcare, IoT, and finance, where federated learning allows organizations to harness the potential of decentralized data while respecting privacy regulations.

We aim to foster cross-disciplinary collaboration and knowledge-sharing that leads to new methods, architectures, and systems that push the boundaries of federated learning research. This session will also shed light on the emerging policy and ethical considerations in the deployment of federated learning models, providing a comprehensive view of this rapidly evolving field. Ultimately, our goal is to build a vibrant community that propels federated learning into a pivotal role in addressing the challenges and opportunities of Big Data analytics.

Topics of interest include, but are not limited to, the following:
* Federated learning algorithms for Big Data processing
* Privacy-preserving mechanisms in federated learning
* Security challenges and solutions in federated learning
* Efficient model aggregation and optimization techniques
* Applications of federated learning in healthcare, finance, and IoT
* Data governance and compliance in federated learning systems
* Challenges and solutions for model updates in non-IID data distributions
* Resource-efficient federated learning for edge devices
* Collaborative learning frameworks for multi-institutional Big Data analytics
* Evaluation metrics and benchmarking for federated learning systems
* Novel architectures and platforms for federated learning deployment
* Adaptive and personalized federated learning models


Special Session Organizers
* Prof. Francesco Piccialli, University of Naples Federico II, Italy
* Dr. Diletta Chiaro, University of Naples Federico II, Italy
* Prof. David Camacho, Universidad Politecnica de Madrid, Spain
* Prof. Antonella Guzzo, University of Calabria, Italy
* Prof. Jerry Chun-Wei Lin, Western Norway University of Applied Sciences, Norway

Instructions
Paper Submission Please submit a full-length paper (up to 10 page IEEE 2-column format, reference pages counted in the 10 pages), or a short vision paper (up to 5 pages IEEE 2-column format, including references) through the online submission system.
https://wi-lab.com/cyberchair/2024/bigdata24/index.php.

Papers should be formatted to IEEE Computer Society Proceedings Manuscript Formatting Guidelines (see link to "formatting instructions" below).
https://www.ieee.org/conferences/publishing/templates.html

Accepted papers will be published in conference proceedings. All accepted papers must be presented by one of the authors to include the article in the proceedings. If you have any questions about this special session, please feel free to contact us: francesco.piccialli@unina.it