Mihaela van der Schaar

research

∙ 08/09/2023

Do Diffusion Models Suffer Error Propagation? Theoretical Analysis and Consistency Regularization

While diffusion models have achieved promising performances in data synt...

0 Yangming Li, et al. ∙

research

∙ 06/08/2023

Interpretable Medical Diagnostics with Structured Data Extraction by Large Language Models

Tabular data is often hidden in text, particularly in medical diagnostic...

12 Aleksa Bisercic, et al. ∙

research

∙ 06/07/2023

Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Time

Machine learning (ML) holds great potential for accurately forecasting t...

2 Toon Vanderschueren, et al. ∙

research

∙ 06/07/2023

U-PASS: an Uncertainty-guided deep learning Pipeline for Automated Sleep Staging

As machine learning becomes increasingly prevalent in critical fields su...

11 Elisabeth R. M. Heremans, et al. ∙

research

∙ 05/31/2023

Learning Representations without Compositional Assumptions

This paper addresses unsupervised representation learning on tabular dat...

7 Tennison Liu, et al. ∙

research

∙ 05/16/2023

Synthetic data, real errors: how (not) to publish and use synthetic data

Generating synthetic data through generative models is gaining interest ...

1 Boris van Breugel, et al. ∙

research

∙ 04/13/2023

Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance

Interpretability methods are valuable only if their explanations faithfu...

3 Jonathan Crabbé, et al. ∙

research

∙ 04/07/2023

Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Data

Generating synthetic data through generative models is gaining interest ...

1 Boris van Breugel, et al. ∙

research

∙ 04/07/2023

Machine Learning with Requirements: a Manifesto

In the recent years, machine learning has made great advancements that h...

7 Eleonora Giunchiglia, et al. ∙

research

∙ 03/09/2023

TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization

Despite their success with unstructured data, deep neural networks are n...

16 Alan Jeffares, et al. ∙

research

∙ 03/03/2023

Causal Deep Learning

Causality has the potential to truly transform the way we solve a large ...

0 Jeroen Berrevoets, et al. ∙

research

∙ 03/02/2023

Learning machines for health and beyond

Machine learning techniques are effective for building predictive models...

7 Mahed Abroshan, et al. ∙

research

∙ 02/24/2023

T-Phenotype: Discovering Phenotypes of Predictive Temporal Patterns in Disease Progression

Clustering time-series data in healthcare is crucial for clinical phenot...

4 Yuchao Qin, et al. ∙

research

∙ 02/24/2023

Neural Laplace Control for Continuous-time Delayed Systems

Many real-world offline reinforcement learning (RL) problems involve con...

0 Samuel Holt, et al. ∙

research

∙ 02/24/2023

Membership Inference Attacks against Synthetic Data through Overfitting Detection

Data is the foundation of most science. Unfortunately, sharing data can ...

3 Boris van Breugel, et al. ∙

research

∙ 02/23/2023

Improving Adaptive Conformal Prediction Using Self-Supervised Learning

Conformal prediction is a powerful distribution-free tool for uncertaint...

26 Nabeel Seedat, et al. ∙

research

∙ 02/23/2023

Understanding the Impact of Competing Events on Heterogeneous Treatment Effect Estimation from Time-to-Event Data

We study the problem of inferring heterogeneous treatment effects (HTEs)...

0 Alicia Curth, et al. ∙

research

∙ 02/06/2023

In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect Estimation

Personalized treatment effect estimates are often of interest in high-st...

2 Alicia Curth, et al. ∙

research

∙ 01/28/2023

TemporAI: Facilitating Machine Learning Innovation in Time Domain Tasks for Medicine

TemporAI is an open source Python software library for machine learning ...

1 Evgeny S. Saveliev, et al. ∙

research

∙ 01/26/2023

Joint Training of Deep Ensembles Fails Due to Learner Collusion

Ensembles of machine learning models have been well established as a pow...

3 Alan Jeffares, et al. ∙

research

∙ 01/18/2023

Synthcity: facilitating innovative use cases of synthetic data in different data modalities

Synthcity is an open-source software package for innovative use cases of...

9 Zhaozhi Qian, et al. ∙

research

∙ 12/01/2022

Navigating causal deep learning

Causal deep learning (CDL) is a new and important research area in the l...

7 Jeroen Berrevoets, et al. ∙

research

∙ 11/11/2022

Practical Approaches for Fair Learning with Multitype and Multivariate Sensitive Attributes

It is important to guarantee that machine learning algorithms deployed i...

5 Tennison Liu, et al. ∙

research

∙ 11/09/2022

DC-Check: A Data-Centric AI checklist to guide the development of reliable machine learning systems

While there have been a number of remarkable breakthroughs in machine le...

14 Nabeel Seedat, et al. ∙

research

∙ 10/24/2022

Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data

High model performance, on average, can hide that models may systematica...

6 Nabeel Seedat, et al. ∙

research

∙ 10/21/2022

AutoPrognosis 2.0: Democratizing Diagnostic and Prognostic Modeling in Healthcare with Automated Machine Learning

Diagnostic and prognostic models are increasingly important in medicine ...

30 Fergus Imrie, et al. ∙

research

∙ 10/11/2022

Synthetic Model Combination: An Instance-wise Approach to Unsupervised Ensemble Learning

Consider making a prediction over new test data without any opportunity ...

8 Alex J. Chan, et al. ∙

research

∙ 10/08/2022

Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation

Consider the problem of improving the estimation of conditional average ...

12 Ioana Bica, et al. ∙

research

∙ 09/22/2022

Concept Activation Regions: A Generalized Framework For Concept-Based Explanations

Concept-based explanations permit to understand the predictions of a dee...

4 Jonathan Crabbé, et al. ∙

research

∙ 08/11/2022

Adaptively Identifying Patient Populations With Treatment Benefit in Clinical Trials

We study the problem of adaptively identifying patient subpopulations th...

8 Alicia Curth, et al. ∙

research

∙ 08/02/2022

DAPDAG: Domain Adaptation via Perturbed DAG Reconstruction

Leveraging labelled data from multiple domains to enable prediction in a...

3 Yanke Li, et al. ∙

research

∙ 07/11/2022

DAUX: a Density-based Approach for Uncertainty eXplanations

Uncertainty quantification (UQ) is essential for creating trustworthy ma...

18 Hao Sun, et al. ∙

research

∙ 06/21/2022

D-CIPHER: Discovery of Closed-form PDEs

Closed-form differential equations, including partial differential equat...

0 Krzysztof Kacprzyk, et al. ∙

research

∙ 06/16/2022

Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability

Estimating personalized effects of treatments is a complex, yet pervasiv...

1 Jonathan Crabbé, et al. ∙

research

∙ 06/16/2022

Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations

Estimating counterfactual outcomes over time has the potential to unlock...

4 Nabeel Seedat, et al. ∙

research

∙ 06/15/2022

HyperImpute: Generalized Iterative Imputation with Automatic Model Selection

Consider the problem of imputing missing values in a dataset. One the on...

11 Daniel Jarrett, et al. ∙

research

∙ 06/13/2022

Differentiable and Transportable Structure Learning

We are interested in unsupervised structure learning with a particular f...

2 Jeroen Berrevoets, et al. ∙

research

∙ 06/10/2022

Neural Laplace: Learning diverse classes of differential equations in the Laplace domain

Neural Ordinary Differential Equations model dynamical systems with ODEs...

2 Samuel Holt, et al. ∙

research

∙ 03/15/2022

POETREE: Interpretable Policy Learning with Adaptive Decision Trees

Building models of human decision-making from observed behaviour is crit...

1 Alizée Pace, et al. ∙

research

∙ 03/14/2022

Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies

Human decision making is well known to be imperfect and the ability to a...

1 Alex J. Chan, et al. ∙

research

∙ 03/03/2022

Label-Free Explainability for Unsupervised Models

Unsupervised black-box models are challenging to interpret. Indeed, most...

12 Jonathan Crabbé, et al. ∙

research

∙ 02/25/2022

Combining Observational and Randomized Data for Estimating Heterogeneous Treatment Effects

Estimating heterogeneous treatment effects is an important problem acros...

1 Tobias Hatt, et al. ∙

research

∙ 02/21/2022

Inferring Lexicographically-Ordered Rewards from Preferences

Modeling the preferences of agents over a set of alternatives is a princ...

5 Alihan Hüyük, et al. ∙

research

∙ 02/17/2022

Data-SUITE: Data-centric identification of in-distribution incongruous examples

Systematic quantification of data quality is critical for consistent mod...

5 Nabeel Seedat, et al. ∙

research

∙ 02/04/2022

To Impute or not to Impute? – Missing Data in Treatment Effect Estimation

Missing data is a systemic problem in practical scenarios that causes no...

5 Jeroen Berrevoets, et al. ∙

research

∙ 12/07/2021

Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Time

Choosing the best treatment-plan for each individual patient requires ac...

3 Jeroen Berrevoets, et al. ∙

research

∙ 11/04/2021

MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanisms

Missing data is an important problem in machine learning practice. Start...

25 Trent Kyono, et al. ∙

research

∙ 10/28/2021

Explaining Latent Representations with a Corpus of Examples

Modern machine learning models are complicated. Most of them rely on con...

13 Jonathan Crabbé, et al. ∙

research

∙ 10/26/2021

SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data

We study the problem of inferring heterogeneous treatment effects from t...

4 Alicia Curth, et al. ∙

research

∙ 10/25/2021

DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks

Machine learning models have been criticized for reflecting unfair biase...

12 Boris van Breugel, et al. ∙

Mihaela van der Schaar

Featured Co-authors