“A breakthrough in machine learning will be worth 10 Microsofts.” ~ Bill Gates

Causal inference and fairness in machine learning:

Guaranteeing fairness without incorporating causal reasoning is a thankless task. I replace the question “Is the hiring process of a company discrimination against women?” by the question “Does gender have a causal effect on the hiring decisions?” and bringing causal reasoning into the studies of fairness to stop discrimination, e.g., against women.

• Khademi, A., and Honavar, V. (2020). Algorithmic Bias in Recidivism Prediction: A Causal Perspective. In: Proceedings of the Thirty-Forth AAAI Conference on Artificial Intelligence (PDF).
• Khademi, A., Lee, S., Foley, D., and Honavar, V. (2019). Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality. In: Proceedings of the 2019 World Wide Web Conference (WWW-19). [PDF]

Machine learning in sleep health:

I am collaborating with Dr. Orfeu Buxton to develop machine learning algorithms for sleep quality assessment from various types of data.

• Khademi, A., El-Manzalawy, Y., Master, L., Buxton, O. M., & Honavar, V. Personalized Sleep Parameters Estimation from Actigraphy: A Machine Learning Approach. In Nature and Science of Sleep (PDF).
• Khademi, A., El-Manzalawy, Y., Buxton, O. M., & Honavar, V. (2018). Toward personalized sleep-wake prediction from actigraphy. In: IEEE EMBS International Conference on Biomedical & Health Informatics (BHI). [PDF] [Slides]