Explore

Collaborative AI: Advancing FL Across Disciplines @ DSAA2025

Special Session on Collaborative AI: Advancing Federated Learning Across Disciplines

More information to come: stay tuned!

Find the important dates

here⁠

⁠

Find the submission instructions

here⁠

⁠

Find main conference page

here⁠

⁠

Overview

This special session explores federated machine learning in increasingly complex distributed environments. As data becomes distributed among numerous users and cannot be centrally collected due to privacy constraints, new challenges emerge. These include learning in heterogeneous systems, effective communication for model updates, and representation of distributed models. We focus on federated learning variants, model compression, adaptive aggregation techniques, and privacy preservation approaches including differential privacy.

The session encourages research on deep learning applications in federated contexts, particularly in IoT, recommendation systems, medicine, automotive, sensor networks, and text processing, with emphasis on balancing privacy, efficiency, and performance.

Important Dates

Submission Deadline: May 2nd, 2025

Acceptance Notification: July 24th, 2025

Camera-ready Submission Deadline: August 21st, 2025

Conference: 9-13 October 2025

Deadlines refer to 23:59 (11:59pm) in the AoE (Anywhere on Earth) time zone.

Topics of Interest

We particularly welcome submissions that bridge research communities and foster interdisciplinary collaboration. Our special session seeks papers presenting novel methods at the intersection of federated learning, distributed intelligence, computational intelligence, and machine learning that promote dialogue across traditional research boundaries. Topics include but are not limited to:

Learning in heterogeneous and distributed systems

Effective communication protocols for model updates in federated environments

Model compression and adaptive model aggregation techniques

Representation learning and distributed model architectures

Approximation methods for distributed data analysis

Federated learning algorithms and variants (Split learning, Gossip Learning, decentralized approaches)

Shapley value attribution and Shapley interactions for model interpretation in federated settings

Multi-modality and multi-view approaches in federated learning

Security and privacy preservation in federated environments

Differential privacy techniques for federated systems

Applications of deep learning in federated contexts

Resource-efficient federated learning for constrained environments

Data analysis and pattern recognition approaches for non-stationary and distributed environments

Submission Instructions

Format: Each paper is limited to ten (10) pages, formatted 2-column U.S. letter style of IEEE Conference template, including figures, tables, and references.

Platform:

OpenReview⁠

⁠

Submission Instructions: Choose Track “Special Session: Collaborative AI: Advancing Federated Learning Across Disciplines” for your OpenReview submission

Submissions will undergo the same rigorous peer-review process as regular conference papers. All accepted full-length papers will be published by IEEE and will be submitted for inclusion in the IEEE Xplore Digital Library. The conference proceedings will be submitted for EI indexing through INSPEC by IEEE.

Find the complete submission guidelines here:

here⁠

⁠