Call for Special Session on Federated Learning on Big Data
Special Session on Federated Learning on Big Data on December 14-17, 2026, Phoenix, Arizona, USA
Aim and Scope
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 Unlearning methodologies
- Adaptive and personalized federated learning models
- Novel architectures and platforms for federated learning deployment
- Evaluation metrics and benchmarking for federated learning systems
- Collaborative learning frameworks for multi-institutional Big Data analytics
- Resource-efficient federated learning for edge devices
- Challenges and solutions for model updates in non-IID data distributions
- Data governance and compliance in federated learning systems
- Applications of federated learning in healthcare, finance, and IoT
- Efficient model aggregation and optimization techniques
- Security challenges and solutions in federated learning
- Privacy-preserving mechanisms in federated learning
- Federated learning algorithms for Big Data processing
Special Session Organizers
- Prof. David Camacho, Universidad Politecnica de Madrid, Spain
- Dr. Fabio Giampaolo, University of Naples Federico II, Italy
- Dr. Daniela Annunziata, University of Naples Federico II, Italy
- Prof. Francesco Piccialli, University of Naples Federico II, Italy
Important Dates
- Special Session: December 14-17, 2026
- Camera-ready paper due: November 14, 2026
- Notification of acceptance: October 31, 2026
- Paper submission: September 30, 2026
Instructions
Papers should be submitted as a PDF in 2-column IEEE format. Detailed instructions for the authors can be found at the conference website.
Submitted papers will be thoroughly reviewed by members of the Special Session Program Committee for quality, correctness, originality, and relevance. All accepted papers must be presented by one of the authors, who must register. Papers must be submitted via the CyberChair System by selecting the track "Special Session on Federated Learning on Big Data".
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.