Graph mining methods have been investigated for various applications, including financial analysis, traffic prediction, and drug discovery. Despite their great potential in benefiting humans in the real world, recent study shows that existing graph mining methods can leak private information, are vulnerable to adversarial attacks, can inherit and magnify societal bias from training data, and lack interpret ability. In this course, representative graph mining models and their inner mechanisms will be discussed. Then, we will introduce the trustworthy graph mining methods in aspects of privacy, robustness, fairness, and explain ability.
Unlock more information by signing in with your HKUST account.