Federated learning has become increasingly popular as it facilitates collaborative training among multiple clients while preserving their data privacy. In practice, one major challenge of federated learning is to achieve collaborative fairness among the participating clients, because each client’s contribution to the model is usually far from equal due to various reasons. Besides, as machine learning models are deployed in more and more important applications, how to achieve model fairness, that is, to ensure that the trained model has no discrimination against sensitive attributes, has become another critical factor for federated learning. In this tutorial, we discuss formulations and methods such that collaborative fairness, model fairness, and privacy can be fully respected in federated learning. We will review the existing efforts and the latest progress, and discuss a series of potential directions.

1. Federated Learning: A Quick Review
   • Overview
   • Horizontal Federated Learning
   • Vertical Federated Learning
2. Taxonomy of Fairness in Federated Learning
   • Performance Fairness
   • Collaboration Fairness
   • Model Fairness
3. Towards Performance Fairness in Federated Learning
   • Fair Resource Allocation
   • Agnostic Federated Learning
   • Personalization
4. Towards Collaboration Fairness Federated Learning
   • Contribution Measurement
   • Types of Reward
   • Incentive Mechanism
5. Towards Model Fairness in Federated Learning
   • Fairness in Machine Learning
   • Challenges of Training Fair models in Horizontal Federated Leanring
   • Challenges of Training Fair models in Vertical Federated Leanring
6. Conclusions and Future Directions

Zirui Zhou is currently a Senior Principal Researcher at Huawei Technologies Canada. He received his Ph.D. in Systems Engineering and Engineering Management from Chinese University of Hong Kong. Before joining Huawei, he was an assistant professor in the Department of Mathematics at Hong Kong Baptist University. His research interest includes numerical optimization and its applications in machine learning. His research works on convex analysis, optimization theory, and provable non-convex methods have been published in top-tier journals and conferences.

Lingyang Chu (homepage) is an Assistant Professor at the Department of Computing and Software of McMaster University. Before joining McMaster University, he is a principal researcher at Huawei Technologies Canada. His research interest is in the area of data mining and machine learning. He is especially interested in designing novel algorithms to interpret deep neural networks and to protect data privacy and model fairness in modern machine learning frameworks. His research works in large scale graph mining and interpretable AI have been published in top-tier venues.

Changxin Liu is a PhD candidate at the University of Victoria, Canada. In March 2021, he joined Huawei Technologies Canada (Vancouver Research Center) as a research intern. His research interest focuses on distributed optimization and control for networked systems. He is an active reviewer for more than 10 journals and conferences and an Outstanding Reviewer for IEEE Trans. Cybernetics in 2018.

Lanjun Wang now is a Senior Principal Researcher and technical leader of Vancouver Research Centre, Huawei Canada. She received her Ph.D. degree in Electronic Engineering from Tsinghua University in 2011, and in the same year, she joined IBM Research-China as a Staff Researcher. Before that, she was a member of Academic Talent Program 2001 at Tsinghua University and received B.S degree in Math and Physics in 2005. Lanjun's research interests include data mining, analytics, and modeling. She has issued about 20 patents and led more than ten top-quality publications.

Jian Pei is currently a Professor in the School of Computing Science and an associate member of the Department of Statistics and Actuarial Science at Simon Fraser University, Canada. His general areas include data science, big data, data mining, and database systems. His expertise is on developing effective and efficient data analysis techniques for novel data intensive applications. He is recognized as a Fellow of the Royal Society of Canada (RSC), Academy of Science, a Fellow of ACM and a Fellow of IEEE.

Yong Zhang currently is a Distinguished Researcher at Huawei Technologies Canada and leading the big data and intelligence platform lab at Vancouver research center. Prior to that, he was a postdoctoral research fellow at Stanford University, USA. His research interests include large scale numerical optimization and machine learning. His research works have been published in top-tier journals and conferences.