1 code implementation • NeurIPS 2023 • Mark Mazumder, Colby Banbury, Xiaozhe Yao, Bojan Karlaš, William Gaviria Rojas, Sudnya Diamos, Greg Diamos, Lynn He, Alicia Parrish, Hannah Rose Kirk, Jessica Quaye, Charvi Rastogi, Douwe Kiela, David Jurado, David Kanter, Rafael Mosquera, Juan Ciro, Lora Aroyo, Bilge Acun, Lingjiao Chen, Mehul Smriti Raje, Max Bartolo, Sabri Eyuboglu, Amirata Ghorbani, Emmett Goodman, Oana Inel, Tariq Kane, Christine R. Kirkpatrick, Tzu-Sheng Kuo, Jonas Mueller, Tristan Thrush, Joaquin Vanschoren, Margaret Warren, Adina Williams, Serena Yeung, Newsha Ardalani, Praveen Paritosh, Lilith Bat-Leah, Ce Zhang, James Zou, Carole-Jean Wu, Cody Coleman, Andrew Ng, Peter Mattson, Vijay Janapa Reddi
Machine learning research has long focused on models rather than datasets, and prominent datasets are used for common ML tasks without regard to the breadth, difficulty, and faithfulness of the underlying problems.
no code implementations • 10 Nov 2021 • Amirata Ghorbani, Dina Berenbaum, Maor Ivgi, Yuval Dafna, James Zou
We address this limitation by introducing Feature Vectors, a new global interpretability method designed for tabular datasets.
no code implementations • 16 Apr 2021 • Amirata Ghorbani, James Zou, Andre Esteva
In this work, we introduce Active Data Shapley (ADS) -- a filtering layer for batch active learning that significantly increases the efficiency of active learning by pre-selecting, using a linear time computation, the highest-value points from an unlabeled dataset.
no code implementations • 15 Apr 2021 • Ramin Ansari, Amirata Ghorbani
As a result, these models are capable of making accurate predictions of the molecular properties without the time consuming process of running an experiment on each molecule.
no code implementations • 15 Oct 2020 • Siyi Tang, Amirata Ghorbani, Rikiya Yamashita, Sameer Rehman, Jared A. Dunnmon, James Zou, Daniel L. Rubin
In this study, we used data Shapley, a data valuation metric, to quantify the value of training data to the performance of a pneumonia detection algorithm in a large chest X-ray dataset.
no code implementations • ICLR 2021 • Linjun Zhang, Zhun Deng, Kenji Kawaguchi, Amirata Ghorbani, James Zou
For robustness, we show that minimizing the Mixup loss corresponds to approximately minimizing an upper bound of the adversarial loss.
no code implementations • 15 Jun 2020 • Zhun Deng, Linjun Zhang, Amirata Ghorbani, James Zou
In this work, we investigate how adversarial robustness can be enhanced by leveraging out-of-domain unlabeled data.
1 code implementation • Nature 2020 • David Ouyang, Bryan He, Amirata Ghorbani, Neal Yuan, Joseph Ebinger, Curtis P. Langlotz, Paul A. Heidenreich, Robert A. Harrington, David H. Liang, Euan A. Ashley, James Y. Zou
Accurate assessment of cardiac function is crucial for the diagnosis of cardiovascular disease, screening for cardiotoxicity and decisions regarding the clinical management of patients with a critical illness.
Ranked #2 on on Echonet-Dynamic
no code implementations • ICML 2020 • Amirata Ghorbani, Michael P. Kim, James Zou
Shapley value is a classic notion from game theory, historically used to quantify the contributions of individuals within groups, and more recently applied to assign values to data points when training machine learning models.
1 code implementation • NeurIPS 2020 • Amirata Ghorbani, James Zou
We develop Neuron Shapley as a new framework to quantify the contribution of individual neurons to the prediction and performance of a deep network.
no code implementations • 20 Nov 2019 • Amirata Ghorbani, Vivek Natarajan, David Coz, Yu-An Liu
Despite the recent success in applying supervised deep learning to medical imaging tasks, the problem of obtaining large and diverse expert-annotated datasets required for the development of high performant models remains particularly challenging.
no code implementations • 9 Oct 2019 • Gal Yona, Amirata Ghorbani, James Zou
We propose Extended Shapley as a principled framework for this problem, and experiment empirically with how it can be used to address questions of ML accountability.
6 code implementations • 5 Apr 2019 • Amirata Ghorbani, James Zou
As data becomes the fuel driving technological and economic growth, a fundamental challenge is how to quantify the value of data in algorithmic predictions and decisions.
2 code implementations • NeurIPS 2019 • Amirata Ghorbani, James Wexler, James Zou, Been Kim
Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions.
no code implementations • 17 Jul 2018 • Jaime Roquero Gimenez, Amirata Ghorbani, James Zou
This is often impossible to do from purely observational data, and a natural relaxation is to identify features that are correlated with the outcome even conditioned on all other observed features.
1 code implementation • 31 May 2018 • Michael P. Kim, Amirata Ghorbani, James Zou
Prediction systems are successfully deployed in applications ranging from disease diagnosis, to predicting credit worthiness, to image recognition.
no code implementations • ICLR 2018 • Amirata Ghorbani, Abubakar Abid, James Zou
In this paper, we show that interpretation of deep learning predictions is extremely fragile in the following sense: two perceptively indistinguishable inputs with the same predicted label can be assigned very different}interpretations.
2 code implementations • 29 Oct 2017 • Amirata Ghorbani, Abubakar Abid, James Zou
In this paper, we show that interpretation of deep learning predictions is extremely fragile in the following sense: two perceptively indistinguishable inputs with the same predicted label can be assigned very different interpretations.