research
∙
06/12/2023
On the Robustness of Removal-Based Feature Attributions
To explain complex models based on their inputs, many feature attributio...
share
research
∙
06/05/2023
Estimating Conditional Mutual Information for Dynamic Feature Selection
Dynamic feature selection, where we sequentially query features to make ...
research
∙
01/02/2023
Learning to Maximize Mutual Information for Dynamic Feature Selection
Feature selection helps reduce data acquisition costs in ML, but the sta...
research
∙
09/30/2022
Contrastive Corpus Attribution for Explaining Representations
Despite the widespread use of unsupervised models, very few methods are ...
research
∙
07/15/2022
Algorithms to estimate Shapley value feature attributions
Feature attributions based on the Shapley value are popular for explaini...
research
∙
06/10/2022
Learning to Estimate Shapley Values with Vision Transformers
Transformers have become a default architecture in computer vision, but ...
research
∙
05/05/2022
A Deep Bayesian Bandits Approach for Anticancer Therapy: Exploration via Functional Prior
Learning personalized cancer treatment with machine learning holds great...
research
∙
02/21/2022
Moment Matching Deep Contrastive Latent Variable Models
In the contrastive analysis (CA) setting, machine learning practitioners...
research
∙
07/15/2021
FastSHAP: Real-Time Shapley Value Estimation
Shapley values are widely used to explain black-box models, but they are...
research
∙
06/14/2021
Pitfalls of Explainable ML: An Industry Perspective
As machine learning (ML) systems take a more prominent and central role ...
research
∙
04/30/2021
Explaining a Series of Models by Propagating Local Feature Attributions
Pipelines involving a series of several machine learning models (e.g., s...
research
∙
12/02/2020
Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regression
The Shapley value solution concept from cooperative game theory has beco...
research
∙
11/21/2020
Explaining by Removing: A Unified Framework for Model Explanation
Researchers have proposed a wide variety of model explanation approaches...
research
∙
11/06/2020
Feature Removal Is a Unifying Principle for Model Explanation Methods
Researchers have proposed a wide variety of model explanation approaches...
research
∙
06/29/2020
True to the Model or True to the Data?
A variety of recent papers discuss the application of Shapley values, a ...
research
∙
04/01/2020
Understanding Global Feature Contributions Through Additive Importance Measures
Understanding the inner workings of complex machine learning models is a...
research
∙
02/12/2020
Deep Transfer Learning for Physiological Signals
Deep learning is increasingly common in healthcare, yet transfer learnin...
research
∙
02/10/2020
Explaining Explanations: Axiomatic Feature Interactions for Deep Networks
Recent work has shown great promise in explaining neural network behavio...
research
∙
01/13/2020
An Adversarial Approach for the Robust Classification of Pneumonia from Chest Radiographs
While deep learning has shown promise in the domain of disease classific...
research
∙
12/20/2019
Learned Feature Attribution Priors
Deep learning models have achieved breakthrough successes in domains whe...
research
∙
11/27/2019
Explaining Models by Propagating Shapley Values of Local Components
In healthcare, making the best possible predictions with complex models ...
research
∙
06/25/2019
Learning Explainable Models Using Attribution Priors
Two important topics in deep learning both involve incorporating humans ...
research
∙
05/11/2019
Explainable AI for Trees: From Local Explanations to Global Understanding
Tree-based machine learning models such as random forests, decision tree...
research
∙
02/12/2018
Consistent Individualized Feature Attribution for Tree Ensembles
Interpreting predictions from tree ensemble methods such as gradient boo...
research
∙
01/23/2018
Hybrid Gradient Boosting Trees and Neural Networks for Forecasting Operating Room Data
Time series data constitutes a distinct and growing problem in machine l...
research
∙
01/23/2018
Hybrid Gradient Boosting Trees and NeuralNetworks for Forecasting Operating Room Data
Time series data constitutes a distinct and growing problem in machine l...
research
∙
12/02/2017
Anesthesiologist-level forecasting of hypoxemia with only SpO2 data using deep learning
We use a deep learning model trained only on a patient's blood oxygenati...
research
∙
06/19/2017
Consistent feature attribution for tree ensembles
It is critical in many applications to understand what features are impo...
research
∙
05/22/2017
A Unified Approach to Interpreting Model Predictions
Understanding why a model makes a certain prediction can be as crucial a...
research
∙
11/22/2016
An unexpected unity among methods for interpreting model predictions
Understanding why a model made a certain prediction is crucial in many d...
research
∙
02/28/2014
Learning Graphical Models With Hubs
We consider the problem of learning a high-dimensional graphical model i...
research
∙
03/21/2013