Special Session on Federated Learning on Big Data
December 14–17, 2026 – Phoenix, Arizona, USA

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
- Topics include, but are not limited to:
- Federated learning algorithms for Big Data
- Privacy-preserving mechanisms
- Security challenges and solutions
- Model aggregation and optimization
- Applications in healthcare, finance, and IoT
- Data governance and compliance
- Non-IID data challenges
- Resource-efficient federated learning
- Multi-institutional collaborative learning
- Evaluation metrics and benchmarking
- Architectures and platforms for deployment
- Personalized federated learning
- Federated unlearning


If you have any questions about this special session, please feel free to contact us: francesco.piccialli@unina.it
daniela.annunziata@unina.it