NetFair: Fair Network Learning

The network learning and mining literature is rich in answering who/what types of questions. For example, who is most influential? Which items should be recommended to a given user? Despite the remarkable progress over the past decades, how to make network learning results and processes explainable, transparent, and fair to end users is a largely open question. The ultimate goal of this research is to build a computational foundation for fair network learning. Specifically, this research will develop computational theories, algorithms, and prototype systems in the context of network learning, forming three key pillars of fair network learning, including interpretation, auditing and de-biasing.

Contact: Hanghang Tong