Search Results for author: Jessica Schrouff

Found 14 papers, 3 papers with code

Evaluating Model Bias Requires Characterizing its Mistakes

no code implementations15 Jul 2024 Isabela Albuquerque, Jessica Schrouff, David Warde-Farley, Taylan Cemgil, Sven Gowal, Olivia Wiles

We demonstrate that characterizing (as opposed to simply quantifying) model mistakes across subgroups is pivotal to properly reflect model biases, which are ignored by standard metrics such as worst-group accuracy or accuracy gap.

Attribute model

Mind the Graph When Balancing Data for Fairness or Robustness

no code implementations25 Jun 2024 Jessica Schrouff, Alexis Bellot, Amal Rannen-Triki, Alan Malek, Isabela Albuquerque, Arthur Gretton, Alexander D'Amour, Silvia Chiappa

Failures of fairness or robustness in machine learning predictive settings can be due to undesired dependencies between covariates, outcomes and auxiliary factors of variation.

Fairness

FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch

no code implementations7 Jun 2024 Virginia Aglietti, Ira Ktena, Jessica Schrouff, Eleni Sgouritsa, Francisco J. R. Ruiz, Alan Malek, Alexis Bellot, Silvia Chiappa

The sample efficiency of Bayesian optimization algorithms depends on carefully crafted acquisition functions (AFs) guiding the sequential collection of function evaluations.

Bayesian Optimization global-optimization +2

Adapting to Latent Subgroup Shifts via Concepts and Proxies

no code implementations21 Dec 2022 Ibrahim Alabdulmohsin, Nicole Chiou, Alexander D'Amour, Arthur Gretton, Sanmi Koyejo, Matt J. Kusner, Stephen R. Pfohl, Olawale Salaudeen, Jessica Schrouff, Katherine Tsai

We show that the optimal target predictor can be non-parametrically identified with the help of concept and proxy variables available only in the source domain, and unlabeled data from the target.

Unsupervised Domain Adaptation

Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing

no code implementations21 Jul 2022 Alexander Brown, Nenad Tomasev, Jan Freyberg, YuAn Liu, Alan Karthikesalingam, Jessica Schrouff

Machine learning (ML) holds great promise for improving healthcare, but it is critical to ensure that its use will not propagate or amplify health disparities.

Fairness Multi-Task Learning

A Reduction to Binary Approach for Debiasing Multiclass Datasets

1 code implementation31 May 2022 Ibrahim Alabdulmohsin, Jessica Schrouff, Oluwasanmi Koyejo

We propose a novel reduction-to-binary (R2B) approach that enforces demographic parity for multiclass classification with non-binary sensitive attributes via a reduction to a sequence of binary debiasing tasks.

Disability prediction in multiple sclerosis using performance outcome measures and demographic data

no code implementations8 Apr 2022 Subhrajit Roy, Diana Mincu, Lev Proleev, Negar Rostamzadeh, Chintan Ghate, Natalie Harris, Christina Chen, Jessica Schrouff, Nenad Tomasev, Fletcher Lee Hartsell, Katherine Heller

To the best of our knowledge, our results are the first to show that it is possible to predict disease progression using POMs and demographic data in the context of both clinical trials and smartphone-base studies by using two datasets.

Benchmarking BIG-bench Machine Learning

Healthsheet: Development of a Transparency Artifact for Health Datasets

1 code implementation26 Feb 2022 Negar Rostamzadeh, Diana Mincu, Subhrajit Roy, Andrew Smart, Lauren Wilcox, Mahima Pushkarna, Jessica Schrouff, Razvan Amironesei, Nyalleng Moorosi, Katherine Heller

Our findings from the interviewee study and case studies show 1) that datasheets should be contextualized for healthcare, 2) that despite incentives to adopt accountability practices such as datasheets, there is a lack of consistency in the broader use of these practices 3) how the ML for health community views datasheets and particularly \textit{Healthsheets} as diagnostic tool to surface the limitations and strength of datasets and 4) the relative importance of different fields in the datasheet to healthcare concerns.

Best of both worlds: local and global explanations with human-understandable concepts

no code implementations16 Jun 2021 Jessica Schrouff, Sebastien Baur, Shaobo Hou, Diana Mincu, Eric Loreaux, Ralph Blanes, James Wexler, Alan Karthikesalingam, Been Kim

While there are many methods focused on either one, few frameworks can provide both local and global explanations in a consistent manner.

Concept-based model explanations for Electronic Health Records

1 code implementation3 Dec 2020 Diana Mincu, Eric Loreaux, Shaobo Hou, Sebastien Baur, Ivan Protsyuk, Martin G Seneviratne, Anne Mottram, Nenad Tomasev, Alan Karthikesanlingam, Jessica Schrouff

Recurrent Neural Networks (RNNs) are often used for sequential modeling of adverse outcomes in electronic health records (EHRs) due to their ability to encode past clinical states.

Time Series Time Series Analysis

Inferring Javascript types using Graph Neural Networks

no code implementations16 May 2019 Jessica Schrouff, Kai Wohlfahrt, Bruno Marnette, Liam Atkinson

The recent use of `Big Code' with state-of-the-art deep learning methods offers promising avenues to ease program source code writing and correction.

Code Repair Graph Neural Network

Interpreting weight maps in terms of cognitive or clinical neuroscience: nonsense?

no code implementations30 Apr 2018 Jessica Schrouff, Janaina Mourao-Miranda

Since machine learning models have been applied to neuroimaging data, researchers have drawn conclusions from the derived weight maps.

Cannot find the paper you are looking for? You can Submit a new open access paper.