Skip to content

About me

“It is better to know how to learn than to know” – Dr. Seuss

Hi there, Penn Stater in heart here. I’m currently a Senior Data Scientist at IEEE. Before this role, I was a Machine Learning and Robotics Engineer at Ford Research. Before joining Ford, I received a Ph.D. of Informatics from the college of Information Sciences and Technology (IST) at the Pennsylvania State University. I further hold a Ph.D. minor in Statistics and a Master of Science in Information Sciences and Technology from Penn State. I was advised by Dr. Vasant Honavar (IST) and Dr. Aleksandra Slavkovic (Statistics). Before joining Penn State, I received a Master’s degree in artificial intelligence and a Bachelor’s degree in computer software engineering.

I specialize in machine learning, data science, and artificial intelligence. During Ph.D., I have a focus on the following areas: (i) Model monitoring and robustness in AI and ML (ii) Causal inference in machine learning, (iii) Fairness and interpretation in machine learning, and (iv) Applying machine learning to health care. I am a member of the Artificial Intelligence Research Lab, a fellow at the Biomedical Big Data Training Program, a Scholar at the Institute for Computational and Data Sciences, and an AI Student Ambassador at Intel Co. You can find my CV here.

Google Scholar page: Click here.

Media Coverage: The paper “Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality” made its way to the news at (non-exhaustive):

  1. EurekAlert! by AAAS,
  2. Science Daily
  3. The Science Times
  4. Phys.org,
  5. Penn State News.

Watch me:

Link to a short video of me at the College of IST at Penn State: Meet Aria Khademi

News:

  • I will soon join Ford Motor Company as a Research Engineer.
  • I successfully defended my Ph.D. (June 2021).
  • I was recognized as top 10% reviewer for NeurIPS-2020 (Oct 2020).
  • I received an M.S. degree in Information Sciences and Technology from Penn State (Spring 2020).
  • Presented my work on “Algorithmic Bias in Recidivism Prediction: A Causal Perspective” at AAAI-20 (Feb 2020).
  • I was recognized as a top 5% Excellent Reviewer for Neurips 2019 Workshop on Machine Learning for Health (Nov 2019).
  • My extended abstract “Algorithmic Bias in Recidivism Prediction: A Causal Perspective” was accepted to AAAI (Oct 2020).
  • My paper “Personalized Sleep Parameters Estimation from Actigraphy: A Machine Learning Approach” has been accepted for publication in Nature and Science of Sleep (Oct 2019).
  • Successfully passed my proposal defense (Aug 2019).
  • My request for a graduate minor in Statistics at Penn State got approved (June 2019).
  • My paper “Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality” got accepted to WWW-2019.
  • My article on the future of AI research got published on Intel’s Medium (Click here).
  • Became an AI Student Ambassador for Intel (July 2018).
  • After a long time of procrastination, finally wrote about my favorite teachers, under education on the left (July 2018).
  • Attended the workshop by Center for Causal Discovery at Carnegie Mellon University (June 2018).
  • Started writing about my favorite movies in the movie blog on the left (June 2018).
  • Successfully passed 32 credits in courses for PhD (May 2018).
  • Served as a judge for Penn State’s undergraduate poster exhibition (Apr 2018).
  • Started writing about music theory in the music blog on the left (Apr 2018).
  • Presented my work on sleep-wake prediction to the Biomedical Big Data to Knowledge spring retreat (Apr 2018).
  • My paper on personalized sleep-wake prediction from actigraphy was published in BHI 2018 (Mar 2018).

Peer-Reviewed Publications: 

  1. Khademi, A., Honavar, V. (2020) Algorithmic bias in recidivism prediction: A causal perspective. In: Proceedings of the AAAI Conference on Artificial Intelligence, Student Abstract Program (Acceptance rate: 48%).
  2. Khademi, A., El-Manzalawy, Y., Master, L., Buxton, O. M., Honavar, V. G. (2019). Personalized sleep parameters estimation from actigraphy: A machine learning approach. In: Nature and Science of Sleep, Volume 11, pp. 387-399.
  3. Khademi, A., Lee, S., Foley, D., Honavar, V. (2019). Fairness in algorithmic decision making: An excursion through the lens of causality. In: Proceedings of the 2019 Conference on The World Wide Web (WWW-19) pp. 2907-2914 (Acceptance rate: 20%, See Media Coverage above).
  4. Khademi, A., EL-Manzalawy, Y., Buxton, O., Honavar, V. (2018). Toward personalized sleep-wake prediction from actigraphy. In: IEEE EMBS International Conference on Biomedical and Health Informatics (BHI) pp. 414-417 (Oral presentation acceptance rate: 14%).

Pre-Prints:

  1. Khademi, A., Honavar, V. (2020) A Causal Lens for Peeking into Black Box Predictive Models: Predictive Model Interpretation via Causal Attribution.
  2. Seto, C., Khademi, A., Graif, C., Honavar, V. (2020) Commuting Network Spillovers and COVID-19 Deaths Across US Counties.

Professional Service: 

Paper reviewer: NeurIPS-21, ICML-21, ICLR-21, NeurIPS-20, ICML-20, ACM CHIL-20 (Program Committee), NeurIPS-19, PLOS ONE, WMSCI-19.

Invited judge: Penn State official undergraduate poster exhibition (2018).

Hobbies:

I play music, read books, watch movies, and exercise in my free time. Read my music and movie blogs on the left if you will.

Skip to toolbar