Call For Papers

IJCNN'24 Special Session on Trustworthy Federated Learning: in the Era of Foundation Models

FL@FM-IJCNN'24

URL: https://federated-learning.org/fl@fm-ijcnn-2024/
Event Date: 2024-06-30 ~ 2024-07-05
Submission Date: 2024-01-15
Location: Yokohama, Japan

Data Mining & Analysis Artificial Intelligence Engineering & Computer Science (General)

Federated Learning (FL) is an emerging machine learning paradigm that allows multiple end-users to collaboratively train models without sharing their private data. Existing FL frameworks are undergoing a significant change fueled by Foundation Models (FM), which presents a unique opportunity to unlock new possibilities, challenges, and applications in AI research. FL can be a beneficial tool to address the shortage of high-quality legalized data required by FM training. Meanwhile, FM can empower existing FL systems to alleviate performance degradation problems and lead to a better balance between generalization and personalization, diversity and fidelity. A robust, trustworthy FL platform can be established by examining the interplay between FL and FM, allowing them to benefit each other mutually. Also, it is necessary to overcome potential challenges incurred by original heterogeneity issues, high communication and computation costs, and privacy and security issues in FL.

This special session on trustworthy FL aims to explore recent advances in the intersection of the Foundation Model (FM) and Federated Learning (FL), inspiring future research that can enhance both fields and propel the development of trustworthy AI systems. We invite papers to present novel ideas, showcase potential applications, and discuss promising directions in this research field. We welcome contributions on all aspects of trustworthy FL, with a special focus on its intersection with foundation models. Topics include but are not limited to:

Algorithmic Advances, Novel Issues, and Open Challenges in FL

Theoretical Analysis for Trustworthy FL

Advancing Trustworthy FL for FM

Robustness and Reliability for Trustworthy FL

Improving FM with Decentralized Data

Heterogeneity in FL and FM

Fairness of FL and FM

Interpretability and Explainability of FL and FM

Personalized FL based on FM

FL Trust Policy and Strategies

Performance Evaluation Methods, Metrics of FL Systems

Tools and Resources (e.g., Benchmark Datasets, Software Libraries, ...)

Security and Privacy of FL for FM (e.g., Differential Privacy, Adversarial Attacks, Poisoning Attacks, Inference Attacks, Data Anonymization, Model Distillation, Secure Multi-Party Computation, etc.)

Applications of FL (e.g., Healthcare, Edge Devices, Advertising, Social Networks, Blockchain, Web Search, etc.)

Submission Instructions

Information on paper submission can be found here: https://2024.ieeewcci.org/submission

All accepted papers will be included in the WCCI-2024 proceedings, published on the IEEE Xplore Digital Library.

Organizers

Guodong Long (University of Technology Sydney, Australia)

Zenglin Xu (Harbin Institute of Technology, China)

Jing Jiang (University of Technology Sydney, Australia)

Yue Tan (University of Technology Sydney, Australia)

Han Yu (Nanyang Technological University, Singapore)

Irwin King (The Chinese University of Hong Kong, Hong Kong)

Event Promotion

2024-06-02 ~ 2024-06-06

2024-08-19 ~ 2024-08-22

IJCNN'24 Special Session on Trustworthy Federated Learning: in the Era of Foundation Models

Call for Papers

Submission Instructions

Organizers

Event Promotion

Journal Promotion