Hi! I am a resident at Microsoft Research AI, working with the Adaptive Systems & Interaction Group. My current research interests include building more reliable machine learning systems, especially through the lens of human-AI interaction and collaboration, as well as re-thinking current data collection techniques.
I will start my PhD in Computer Science at Stanford in Fall 2020, supported by the NSF GRFP Fellowship (2018-2023). I also received my B.S. in Computer Science with a minor in Creative Writing from Stanford in 2018. In my spare time, I love swimming, hiking, creative writing, and photography.
Backward Compatibility in Machine Learning Systems
Megha Srivastava, Besmira Nushi, Ece Kamar, Shital Shah, Eric Horvitz
Knowledge Discovery and Data Mining (KDD) 2020
Robustness to Spurious Correlations via Human Annotations
Megha Srivastava, Tatsunori Hashimoto, Percy Liang
International Conference of Machine Learning (ICML) 2020
Mathematical Notions vs. Human Perception of Fairness:
A Descriptive Approach to Fairness for Machine Learning
Megha Srivastava, Hoda Heidari, Andreas Krause
Knowledge Discovery and Data Mining (KDD) 2019
Fairness Without Demographics in Repeated Loss Minimization
Tatsunori B. Hashimoto, Megha Srivastava, Hongseok Namkoong, Percy Liang
International Conference of Machine Learning (ICML) 2018
Best Paper Runner-Up Award