activity
20172021
most citedCertified Defenses for Data Poisoning Attacks

82 citations · 185 across the 4 of their papers we have counts for

collaborators

9 papers

cs.LG202170 cited

Just Train Twice: Improving Group Robustness without Training Group Information

Evan Zheran Liu, Behzad Haghgoo, Annie S. Chen +5

Standard training via empirical risk minimization (ERM) can produce models that achieve high accuracy on average but low accuracy on certain groups, especially in the presence of s…

cs.LG202130 cited

Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization

John Miller, Rohan Taori, Aditi Raghunathan +6

For machine learning systems to be reliable, we must understand their performance in unseen, out-of-distribution environments. In this paper, we empirically show that out-of-distri…

cs.LG2020

Concept Bottleneck Models

Pang Wei Koh, Thao Nguyen, Yew Siang Tang +4

We seek to learn models that we can interact with using high-level concepts: if the model did not think there was a bone spur in the x-ray, would it still predict severe arthritis?…

cs.CL20203 cited

ExpBERT: Representation Engineering with Natural Language Explanations

Shikhar Murty, Pang Wei Koh, Percy Liang

Suppose we want to specify the inductive bias that married couples typically go on honeymoons for the task of extracting pairs of spouses from text. In this paper, we allow model d…

cs.LG2019

Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization

Shiori Sagawa, Pang Wei Koh, Tatsunori B. Hashimoto +1

Overparameterized neural networks can be highly accurate on average on an i.i.d. test set yet consistently fail on atypical groups of the data (e.g., by learning spurious correlati…

cs.LG2019

Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations

Sawyer Birnbaum, Volodymyr Kuleshov, Zayd Enam +2

Learning representations that accurately capture long-range dependencies in sequential inputs -- including text, audio, and genomic data -- is a key problem in deep learning. Feed-…