The FLUID workshop focuses on tackling key challenges in Federated Learning (FL), such as adaptability and scalability in decentralized AI systems, especially in environments with non-IID data and varied device capabilities. It aims to bridge the gap between theoretical advances and real-world applications by highlighting practical methodologies and case studies. While adaptability, decentralization, and heterogeneity in FL have been extensively explored in academia, a significant gap remains between research and real-world application. Many solutions are limited to simulations, with few scalable systems deployed in industries like healthcare, smart cities, finance, and autonomous systems. FLUID aims to bridge this gap by focusing on practical, actionable solutions that are ready for real-life implementation.
The workshop promotes collaboration among researchers and industry experts to drive innovation in healthcare, autonomous systems, and smart cities. The goal is to advance the deployment of resilient, scalable, and intelligent decentralized systems through FL.
Topics of interest include, but are not limited to:
We welcome different kinds of submissions for the FLUID workshop:
Short Papers: Up to 4 pages (excluding references and appendices), focused on emerging ideas, preliminary results, or innovative concepts in FL, with particular emphasis on challenges such as heterogeneity and adaptability.
Long Papers: Up to 7 pages (excluding references and appendices), offering in-depth contributions that introduce novel algorithms, applications, or theoretical advancements aligned with the workshop’s themes.
All submissions must be in PDF format, adhering to the AAAI formatting and submission guidelines. To ensure a fair review process, all submissions will be evaluated through a double-blind review.