Deep learning

Robust multimodal models have outlier features and encode more concepts

We investigate what makes multimodal models that show good robustness with respect to natural distribution shifts (e.g., zero-shot CLIP) different from models with lower robustness using interpretability.

Jonathan Crabbé, Pau Rodríguez, Vaishaal Shankar, Luca Zappella, Arno Blaas

Robust multimodal models have outlier features and encode more concepts

Explaining the Absorption Features of Deep Learning Hyperspectral Classification Models

Over the past decade, Deep Learning (DL) models have proven to be efficient at classifying remotely sensed Earth Observation (EO) …

Arthur Vandenhoeke, Lennert Antson, Guillem Ballesteros, Jonathan Crabbé, Michal Shimoni

Explaining the Absorption Features of Deep Learning Hyperspectral Classification Models

Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance

We assess the robustness of various interpretability methods by measuring how their explanations change when applying symmetries of the model to the input features.

Jonathan Crabbé, Mihaela van der Schaar

Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance

TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization

We introduce TANGOS, a regularization method that orthogonalizes the gradient attribution of neurons to improve the generalization of deep neural networks on tabular data.

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

Joint Training of Deep Ensembles Fails Due to Learner Collusion

Training deep ensembles via a shared objective results in degenerate behavior.

Alan Jeffares, Tennison Liu, Jonathan Crabbé, Mihaela van der Schaar

Joint Training of Deep Ensembles Fails Due to Learner Collusion

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

We extend existing feature and example importance methods to unsupervised learning.

Jonathan Crabbé, Mihaela van der Schaar

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

Label-Free Explainability for Unsupervised Models

We extend existing feature and example importance methods to unsupervised learning.

Jonathan Crabbé, Mihaela van der Schaar

Label-Free Explainability for Unsupervised Models

Representation Learning

Learning realistic representations of the world.

Representation Learning

Robust Machine Learning

Making sure that machines are doing what they are supposed to do.

Robust Machine Learning

Explaining Latent Representations with a Corpus of Examples

We introduce SimplEx, a case-based reasoning explanation method that permits to decompose latent representations with a corpus of example.

Jonathan Crabbé, Zhaozhi Qian, Fergus Imrie, Mihaela van der Schaar

Explaining Latent Representations with a Corpus of Examples