Fairness in Graph Learning Augmented with Machine Learning: A Survey
A survey of fairness challenges and approaches in machine-learning-augmented graph learning.
Paper ↗
|
Ziqi Xu
Lecturer in Data Science and Artificial Intelligence |
I am a Lecturer in Data Science and Artificial Intelligence at the School of Computing Technologies, RMIT University. Before joining RMIT, I was a CERC Fellow at Data61, CSIRO. I obtained my Ph.D. from University of South Australia and my Master’s degree from The University of Adelaide; these institutions have now been integrated into the Adelaide University. I have a broad interest in Responsible AI, particularly in causal inference, fairness, and explainable AI. My long-term goal is to build machine learning systems that are efficient, robust, fair, and interpretable.
A survey of fairness challenges and approaches in machine-learning-augmented graph learning.
Paper ↗A fairness perspective on artificial intelligence for autonomous vehicles.
Paper ↗Exploring the potential and challenges of foundation models for anomaly detection.
Paper ↗Reviewing explainable GNNs for brain connectivity and dementia biomarkers.