Fairness-aware Learning Over Networks

We live in an era of big data and "small-world", where a large amount of data resides on highly connected networks representing a wide range of physical, biological, and social interdependencies, e.g., social networks, and smart grids. Learning from graph/network data is hence expected to bring significant science and engineering advances along with consequent improvements in quality of life. Node representation learning has demonstrated its effectiveness for various applications on graphs. Particularly, recent developments in graph neural networks and contrastive learning have led to promising results in node representation learning for a number of tasks such as node classification, link prediction. Despite the success of graph learning, fairness is largely under-explored in the field, which may lead to biased results towards underrepresented groups in the networks. To this end, this talk will first introduce novel fairness-aware graph augmentation designs to address fairness issues in learning over graphs. New fairness notions on graphs are introduced, which serve as guidelines for the proposed graph augmentation designs. Furthermore, theoretical analysis is provided to prove that the proposed adaptation schemes can reduce intrinsic bias. Experimental results on real networks are presented to demonstrate that the proposed framework can enhance fairness while providing comparable accuracy to state-of-the-art alternative approaches for node classification, and link prediction tasks.