Search Results for author:
Found 11 papers, 6 papers with code
Error Discovery by Clustering Influence Embeddings
We present a method for identifying groups of test examples -- slices -- on which a model under-performs, a task now known as slice discovery.
Quantifying and mitigating the impact of label errors on model disparity metrics
We empirically assess the proposed approach on a variety of datasets and find significant improvement, compared to alternative approaches, in identifying training inputs that improve a model's disparity metric.
Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation
We investigate whether three types of post hoc model explanations--feature attribution, concept activation, and training point ranking--are effective for detecting a model's reliance on spurious signals in the training data.
Debugging Tests for Model Explanations
For several explanation methods, we assess their ability to: detect spurious correlation artifacts (data contamination), diagnose mislabeled training examples (data contamination), differentiate between a (partially) re-initialized model and a trained one (model contamination), and detect out-of-distribution inputs (test-time contamination).
Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging
Saliency maps have become a widely used method to make deep learning models more interpretable by providing post-hoc explanations of classifiers through identification of the most pertinent areas of the input medical image.
Explaining Explanations to Society
We explore the types of questions that explanatory DNN systems can answer and discuss challenges in building explanatory systems that provide outside explanations for societal requirements and benefit.
Sanity Checks for Saliency Maps
We find that reliance, solely, on visual assessment can be misleading.
Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values
Explaining the output of a complicated machine learning model like a deep neural network (DNN) is a central challenge in machine learning.
Investigating Human + Machine Complementarity for Recidivism Predictions
Dressel and Farid (2018) asked Mechanical Turk workers to evaluate a subset of defendants in the ProPublica COMPAS data for risk of recidivism, and concluded that COMPAS predictions were no more accurate or fair than predictions made by humans.
The (Un)reliability of saliency methods
Saliency methods aim to explain the predictions of deep neural networks.
Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Models
Predictive models are increasingly deployed for the purpose of determining access to services such as credit, insurance, and employment.
