This workshop focuses on the unique challenges of deploying FL systems in real-world, safety- or privacy-critical settings---environments where failure is not an option. Unlike existing FL workshops that emphasize general methods, FLCA emphasizes FL under realistic deployment constraints, including privacy guarantees, adversarial robustness, system-level failures, and regulatory compliance. Our emphasis is on practical FL systems that are scalable, robust, and aligned with real-world operational and infrastructural constraints.
This workshop benefits researchers from both industry and academia, exchanging theoretical knowledge and use-case scenarios that might help design federated learning systems for critical applications.
We encourage both applicative and theoretical contributions, including studies on specific settings and benchmarking tools.
Topics of interest include, but are not limited to:
1)Federated, distributed, and decentralized learning approaches for critical applications such as healthcare, advertising, blockchain, and social networks.
2)Infrastructure and system design for deploying real-world FL pipelines.
3)Techniques for FL across different learning paradigms, such as multi-task learning, meta-learning, semi-supervised learning, self-supervised learning, continual learning, ...
4)Theoretical approaches with realistic assumptions for practical settings.
5)FL with heterogeneous and unbalanced (non-IID) data distributions.
6)Security and privacy in FL systems, including differential privacy, adversarial robustness, trustworthiness, and Machine Unlearning at scale.
7)Secure multi-party computation, trusted execution environments, and high-performance computing for federated computations.
8)Variants of FL and decentralized alternatives, including vertical FL, split learning, and gossip learning.
9)Other non-functional aspects in FL for critical use cases, such as fairness, explainability, and personalization.
10)Tools and resources (e.g., benchmark datasets, software libraries, ...)
Format and Attendance
This 1-day workshop will consist of keynote talks by prominent experts and technical presentations. The workshop will also include both oral and poster presentations of high-quality submissions not selected for oral sessions. The workshop will also include a panel session of industrial experts and academic researchers. If applicable, we issue a Best Paper Award that will get a special mention at the workshop’s conclusion. The workshop anticipates 50 participants, including academic researchers and industry professionals. There are no specific attendance criteria beyond the general AAAI registration requirements. The maximum number of attendees will be determined by the room capacity. Other AAAI attendees who are interested can also attend following AAAI’s related policy.
Submission Requirements
We invite submissions of original research on the previously mentioned aspects of Federated Learning (see the complete list of topics). We accept both short papers (4 pages + references + optional appendix) and long papers (8 pages + references + optional appendix).
FLCA workshop does not have formal proceedings, i.e., it is non-archival. Accepted papers and their review comments will be posted on OpenReview in public (after the end of the review process), while rejected and withdrawn papers and their reviews will remain private.
We welcome submissions from novel research, ongoing (incomplete) projects, as well as recently published results.
Submission site information: OpenReview. The request for a submission site has already been made, but the link has not yet been provided by OpenReview. It will be provided as soon as possible.
Workshop Organizers
Linara Adilova, linara.adilova@tu-dortmund.de
Bruno Casella, bruno.casella@unito.it
Samuele Fonio, samuele.fonio@unito.it
Michael Kamp, michael.kamp@tu-dortmund.de
Mirko Polato, mirko.polato@unito.it
Workshop URL
For more details, check out the FLCA webpage: https://sites.google.com/view/flca