152 citations · 659 across the 17 of their papers we have counts for
17 papers
A sparse identification approach for automating choice models' specification
Amir Ghorbani, Neema Nassir, Patricia Sauri Lavieri +1
The methodology discussed in this paper aims to enhance choice models' comprehensiveness and explanatory power for forecasting choice outcomes. To achieve these, we have developed…
DataPerf: Benchmarks for Data-Centric AI Development
Mark Mazumder, Colby Banbury, Xiaozhe Yao +42
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 faithf…
Beyond Importance Scores: Interpreting Tabular ML by Visualizing Feature Semantics
Amirata Ghorbani, Dina Berenbaum, Maor Ivgi +2
Interpretability is becoming an active research topic as machine learning (ML) models are more widely used to make critical decisions. Tabular data is one of the most commonly used…
Data Shapley Valuation for Efficient Batch Active Learning
Amirata Ghorbani, James Zou, Andre Esteva
Annotating the right set of data amongst all available data points is a key challenge in many machine learning applications. Batch active learning is a popular approach to address…
Accurate Prediction of Free Solvation Energy of Organic Molecules via Graph Attention Network and Message Passing Neural Network from Pairwise Atomistic Interactions
Ramin Ansari, Amirata Ghorbani
Deep learning based methods have been widely applied to predict various kinds of molecular properties in the pharmaceutical industry with increasingly more success. Solvation free…
Data Valuation for Medical Imaging Using Shapley Value: Application on A Large-scale Chest X-ray Dataset
Siyi Tang, Amirata Ghorbani, Rikiya Yamashita +4
The reliability of machine learning models can be compromised when trained on low quality data. Many large-scale medical imaging datasets contain low quality labels extracted from…
How Does Mixup Help With Robustness and Generalization?
Linjun Zhang, Zhun Deng, Kenji Kawaguchi +2
Mixup is a popular data augmentation technique based on taking convex combinations of pairs of examples and their labels. This simple technique has been shown to substantially impr…
Improving Adversarial Robustness via Unlabeled Out-of-Domain Data
Zhun Deng, Linjun Zhang, Amirata Ghorbani +1
Data augmentation by incorporating cheap unlabeled data from multiple domains is a powerful way to improve prediction especially when there is limited labeled data. In this work, w…
A Distributional Framework for Data Valuation
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…
Neuron Shapley: Discovering the Responsible Neurons
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. By accounting for interactions…
DermGAN: Synthetic Generation of Clinical Skin Images with Pathology
Amirata Ghorbani, Vivek Natarajan, David Coz +1
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 deve…
Who's responsible? Jointly quantifying the contribution of the learning algorithm and training data
Gal Yona, Amirata Ghorbani, James Zou
A learning algorithm trained on a dataset is revealed to have poor performance on some subpopulation at test time. Where should the responsibility for this lay? It can be a…
Data Shapley: Equitable Valuation of Data for Machine Learning
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. For examp…
Towards Automatic Concept-based Explanations
Amirata Ghorbani, James Wexler, James Zou +1
Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions. Most of the current explan…
Knockoffs for the mass: new feature importance statistics with false discovery guarantees
Jaime Roquero Gimenez, Amirata Ghorbani, James Zou
An important problem in machine learning and statistics is to identify features that causally affect the outcome. This is often impossible to do from purely observational data, and…
Multiaccuracy: Black-Box Post-Processing for Fairness in Classification
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. Even when the overall accuracy i…
Interpretation of Neural Networks is Fragile
Amirata Ghorbani, Abubakar Abid, James Zou
In order for machine learning to be deployed and trusted in many applications, it is crucial to be able to reliably explain why the machine learning algorithm makes certain predict…