AIConfPaper
← Search

Jonathan Crabbé

14 accepted papers

2024

DAGnosis: Localized Identification of Data Inconsistencies using Structures

Nicolas Huynh, Jeroen Berrevoets, Nabeel Seedat, Jonathan Crabbé, Zhaozhi Qian, Mihaela van der Schaar
AISTATS 2024poster

Identification and appropriate handling of inconsistencies in data at deployment time is crucial to reliably use machine learning models. While recent data-centric methods are able to identify such inconsistencies with respect to the training set, they suffer from two key limitations: (1) suboptimal…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2024

Time Series Diffusion in the Frequency Domain

Jonathan Crabbé, Nicolas Huynh, Jan Pawel Stanczuk, Mihaela van der Schaar
ICML 2024poster

Fourier analysis has been an instrumental tool in the development of signal processing. This leads us to wonder whether this framework could similarly benefit generative modelling. In this paper, we explore this question through the scope of time series diffusion models. More specifically, we analyz…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2023

Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance

Jonathan Crabbé, Mihaela van der Schaar
NeurIPS 2023poster

Interpretability methods are valuable only if their explanations faithfully describe the explained model. In this work, we consider neural networks whose predictions are invariant under a specific symmetry group. This includes popular architectures, ranging from convolutional to graph neural network…

Cited by 8Source ↗PDF ↗Scholar ↗
2023

Joint Training of Deep Ensembles Fails Due to Learner Collusion

Alan Jeffares, Tennison Liu, Jonathan Crabbé, Mihaela van der Schaar
NeurIPS 2023poster

Ensembles of machine learning models have been well established as a powerful method of improving performance over a single model. Traditionally, ensembling algorithms train their base learners independently or sequentially with the goal of optimizing their joint performance. In the case of deep ens…

Cited by 22Source ↗PDF ↗Scholar ↗
2023

TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization

Alan Jeffares, Tennison Liu, Jonathan Crabbé, Fergus Imrie, Mihaela van der Schaar
ICLR 2023poster

Despite their success with unstructured data, deep neural networks are not yet a panacea for structured tabular data. In the tabular domain, their efficiency crucially relies on various forms of regularization to prevent overfitting and provide strong generalization performance. Existing regularizat…

Cited by 34Source ↗PDF ↗Scholar ↗
2023

TRIAGE: Characterizing and auditing training data for improved regression

Nabeel Seedat, Jonathan Crabbé, Zhaozhi Qian, Mihaela van der Schaar
NeurIPS 2023poster

Data quality is crucial for robust machine learning algorithms, with the recent interest in data-centric AI emphasizing the importance of training data characterization. However, current data characterization methods are largely focused on classification settings, with regression settings largely un…

Cited by 8Source ↗PDF ↗Scholar ↗
2023

What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization

Hao Sun, Boris van Breugel, Jonathan Crabbé, Nabeel Seedat, Mihaela van der Schaar
NeurIPS 2023poster

Uncertainty quantification (UQ) is essential for creating trustworthy machine learning models. Recent years have seen a steep rise in UQ methods that can flag suspicious examples, however, it is often unclear what exactly these methods identify. In this work, we propose a framework for categorizing…

Cited by 5Source ↗PDF ↗Scholar ↗
2022

Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability

Jonathan Crabbé, Alicia Curth, Ioana Bica, Mihaela van der Schaar
NeurIPS 2022accept

Estimating personalized effects of treatments is a complex, yet pervasive problem. To tackle it, recent developments in the machine learning (ML) literature on heterogeneous treatment effect estimation gave rise to many sophisticated, but opaque, tools: due to their flexibility, modularity and abili…

Cited by 22Source ↗PDF ↗Scholar ↗
2022

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

Jonathan Crabbé, Mihaela van der Schaar
NeurIPS 2022accept

Concept-based explanations permit to understand the predictions of a deep neural network (DNN) through the lens of concepts specified by users. Existing methods assume that the examples illustrating a concept are mapped in a fixed direction of the DNN's latent space. When this holds true, the concep…

Cited by 68Source ↗PDF ↗Scholar ↗
2022

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

Nabeel Seedat, Jonathan Crabbé, Ioana Bica, Mihaela van der Schaar
NeurIPS 2022accept

High model performance, on average, can hide that models may systematically underperform on subgroups of the data. We consider the tabular setting, which surfaces the unique issue of outcome heterogeneity - this is prevalent in areas such as healthcare, where patients with similar features can have…

Cited by 34Source ↗PDF ↗Scholar ↗
2022

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

Nabeel Seedat, Jonathan Crabbé, Mihaela van der Schaar
ICML 2022spotlight

Systematic quantification of data quality is critical for consistent model performance. Prior works have focused on out-of-distribution data. Instead, we tackle an understudied yet equally important problem of characterizing incongruous regions of in-distribution (ID) data, which may arise from feat…

Cited by 22Source ↗PDF ↗code ↗Scholar ↗
2021

Explaining Latent Representations with a Corpus of Examples

Jonathan Crabbé, Zhaozhi Qian, Fergus Imrie, Mihaela van der Schaar
NeurIPS 2021spotlight

Modern machine learning models are complicated. Most of them rely on convoluted latent representations of their input to issue a prediction. To achieve greater transparency than a black-box that connects inputs to predictions, it is necessary to gain a deeper understanding of these latent representa…

Cited by 49Source ↗PDF ↗code ↗Scholar ↗