6 papers
CEPAE: Conditional Entropy-Penalized Autoencoders for Time Series Counterfactuals
Tomàs Garriga, Gerard Sanz, Eduard Serrahima de Cambra +1
The ability to accurately perform counterfactual inference on time series is crucial for decision-making in fields like finance, healthcare, and marketing, as it allows us to under…
Exactly Computing do-Shapley Values
R. Teal Witter, Álvaro Parafita, Tomas Garriga +4
Structural Causal Models (SCM) are a powerful framework for describing complicated dynamics across the natural sciences. A particularly elegant way of interpreting SCMs is do-Shapl…
CID: Measuring Feature Importance Through Counterfactual Distributions
Eddie Conti, Álvaro Parafita, Axel Brando
Assessing the importance of individual features in Machine Learning is critical to understand the model's decision-making process. While numerous methods exist, the lack of a defin…
Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference
Álvaro Parafita, Tomas Garriga, Axel Brando +1
Among explainability techniques, SHAP stands out as one of the most popular, but often overlooks the causal structure of the problem. In response, do-SHAP employs interventional qu…
Object detection in adverse weather conditions for autonomous vehicles using Instruct Pix2Pix
Unai Gurbindo, Axel Brando, Jaume Abella +1
Enhancing the robustness of object detection systems under adverse weather conditions is crucial for the advancement of autonomous driving technology. This study presents a novel a…
Probing the Embedding Space of Transformers via Minimal Token Perturbations
Eddie Conti, Alejandro Astruc, Alvaro Parafita +1
Understanding how information propagates through Transformer models is a key challenge for interpretability. In this work, we study the effects of minimal token perturbations on th…