Hi. I’m Yiwei Yang.

I am a 2nd year PhD student at the Information School of University of Washington, advised by Bill Howe. I received my undergraduate degree in Computer Science in 2019 from the University of Michigan.

Broadly, my research interests lie at the intersection of interpretability and fairness for machine learning. Recently, I designed a metric and a regularizer for measuring and mitigating procedural unfairness by quantifying the divergence of explanations between different groups. This work is submitted to FAccT 2022 (under review). Currently, I am working on a novel group-level feature visualization technique that can expose the biases of image models.