Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Amirata Ghorbani

Data Shapley Valuation for Efficient Batch Active Learning


Apr 16, 2021
Amirata Ghorbani, James Zou, Andre Esteva


  Access Paper or Ask Questions

Accurate Prediction of Free Solvation Energy of Organic Molecules via Graph Attention Network and Message Passing Neural Network from Pairwise Atomistic Interactions


Apr 15, 2021
Ramin Ansari, Amirata Ghorbani

* 14 pages, 4 figures 

  Access Paper or Ask Questions

Data Valuation for Medical Imaging Using Shapley Value: Application on A Large-scale Chest X-ray Dataset


Oct 15, 2020
Siyi Tang, Amirata Ghorbani, Rikiya Yamashita, Sameer Rehman, Jared A. Dunnmon, James Zou, Daniel L. Rubin


  Access Paper or Ask Questions

How Does Mixup Help With Robustness and Generalization?


Oct 09, 2020
Linjun Zhang, Zhun Deng, Kenji Kawaguchi, Amirata Ghorbani, James Zou


  Access Paper or Ask Questions

Improving Adversarial Robustness via Unlabeled Out-of-Domain Data


Jun 15, 2020
Zhun Deng, Linjun Zhang, Amirata Ghorbani, James Zou


  Access Paper or Ask Questions

A Distributional Framework for Data Valuation


Feb 27, 2020
Amirata Ghorbani, Michael P. Kim, James Zou


  Access Paper or Ask Questions

Neuron Shapley: Discovering the Responsible Neurons


Feb 25, 2020
Amirata Ghorbani, James Zou


  Access Paper or Ask Questions

DermGAN: Synthetic Generation of Clinical Skin Images with Pathology


Nov 20, 2019
Amirata Ghorbani, Vivek Natarajan, David Coz, Yuan Liu

* In full proceedings of NeurIPS ML4H workshop, 2019 

  Access Paper or Ask Questions

Who's responsible? Jointly quantifying the contribution of the learning algorithm and training data


Oct 09, 2019
Gal Yona, Amirata Ghorbani, James Zou


  Access Paper or Ask Questions

Data Shapley: Equitable Valuation of Data for Machine Learning


Apr 05, 2019
Amirata Ghorbani, James Zou


  Access Paper or Ask Questions

Automating Interpretability: Discovering and Testing Visual Concepts Learned by Neural Networks


Feb 07, 2019
Amirata Ghorbani, James Wexler, Been Kim


  Access Paper or Ask Questions

Interpretation of Neural Networks is Fragile


Nov 06, 2018
Amirata Ghorbani, Abubakar Abid, James Zou

* Published as a conference paper at AAAI 2019 

  Access Paper or Ask Questions

Multiaccuracy: Black-Box Post-Processing for Fairness in Classification


Aug 29, 2018
Michael P. Kim, Amirata Ghorbani, James Zou


  Access Paper or Ask Questions

Knockoffs for the mass: new feature importance statistics with false discovery guarantees


Jul 17, 2018
Jaime Roquero Gimenez, Amirata Ghorbani, James Zou


  Access Paper or Ask Questions