Search Results for author:
Found 18 papers, 7 papers with code
Interpretation of Neural Networks is Fragile
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.
INTERPRETATION OF NEURAL NETWORK IS FRAGILE
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.
Multiaccuracy: Black-Box Post-Processing for Fairness in Classification
Prediction systems are successfully deployed in applications ranging from disease diagnosis, to predicting credit worthiness, to image recognition.
Knockoffs for the mass: new feature importance statistics with false discovery guarantees
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.
Towards Automatic Concept-based Explanations
Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions.
Data Shapley: Equitable Valuation of Data for Machine Learning
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.
Who's responsible? Jointly quantifying the contribution of the learning algorithm and training data
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.
DermGAN: Synthetic Generation of Clinical Skin Images with Pathology
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.
Neuron Shapley: Discovering the Responsible Neurons
We develop Neuron Shapley as a new framework to quantify the contribution of individual neurons to the prediction and performance of a deep network.
A Distributional Framework for Data Valuation
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.
Video-based AI for beat-to-beat assessment of cardiac function
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
Improving Adversarial Robustness via Unlabeled Out-of-Domain Data
In this work, we investigate how adversarial robustness can be enhanced by leveraging out-of-domain unlabeled data.
How Does Mixup Help With Robustness and Generalization?
For robustness, we show that minimizing the Mixup loss corresponds to approximately minimizing an upper bound of the adversarial loss.
Data Valuation for Medical Imaging Using Shapley Value: Application on A Large-scale Chest X-ray Dataset
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.
Accurate Prediction of Free Solvation Energy of Organic Molecules via Graph Attention Network and Message Passing Neural Network from Pairwise Atomistic Interactions
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.
Data Shapley Valuation for Efficient Batch Active Learning
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.
Beyond Importance Scores: Interpreting Tabular ML by Visualizing Feature Semantics
We address this limitation by introducing Feature Vectors, a new global interpretability method designed for tabular datasets.
DataPerf: Benchmarks for Data-Centric AI Development
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.
