activity
20182021
most citedRobustness to Spurious Correlations via Human Annotations

26 citations · 26 across the 2 of their papers we have counts for

collaborators

5 papers

cs.CL2021

Question Generation for Adaptive Education

Megha Srivastava, Noah Goodman

Intelligent and adaptive online education systems aim to make high-quality education available for a diverse range of students. However, existing systems usually depend on a pool o…

cs.LG202026 cited

Robustness to Spurious Correlations via Human Annotations

Megha Srivastava, Tatsunori Hashimoto, Percy Liang

The reliability of machine learning systems critically assumes that the associations between features and labels remain similar between training and test distributions. However, un…

cs.LG2020

An Empirical Analysis of Backward Compatibility in Machine Learning Systems

Megha Srivastava, Besmira Nushi, Ece Kamar +2

In many applications of machine learning (ML), updates are performed with the goal of enhancing model performance. However, current practices for updating models rely solely on iso…

cs.CV2018

The Effect of Learning Strategy versus Inherent Architecture Properties on the Ability of Convolutional Neural Networks to Develop Transformation Invariance

Megha Srivastava, Kalanit Grill-Spector

As object recognition becomes an increasingly common ML task, and recent research demonstrating CNNs vulnerability to attacks and small image perturbations necessitate fully unders…

stat.ML2018

Fairness Without Demographics in Repeated Loss Minimization

Tatsunori B. Hashimoto, Megha Srivastava, Hongseok Namkoong +1

Machine learning models (e.g., speech recognizers) are usually trained to minimize average loss, which results in representation disparity---minority groups (e.g., non-native speak…