AI Thrust Seminar| Trustworthy AI from the perspective of Fairness

AI, especially machine learning, often presents statistical discrimination due to non-identical data distribution or resources, leaving certain privileged groups with performance advantages. Regardless of generated on purpose or accidentally, the learning bias exacerbates the existing resource inequity and harms society's fairness. Therefore, the AI community has been putting efforts into guaranteeing AI systems' fairness to mitigate algorithmic bias. 

In this talk, I will focus on the challenge of guaranteeing fairness in distributed setup and introduce some related research. I'll first give an outlook on the trend of distributed learning and common scenarios where bias often occurs, including use cases in different fields and causes of the bias. Then I'll introduce several related proposals to tackle the challenge mentioned above, specifically in federated learning.