DiConStruct: Causal Concept-based Explanations through Black-Box Distillation

no code implementations • 16 Jan 2024 • Ricardo Moreira, Jacopo Bono, Mário Cardoso, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro

Lastly, explanation methods should be efficient and not compromise the performance of the predictive task.

Decision Making

Lightweight Automated Feature Monitoring for Data Streams

no code implementations • 18 Jul 2022 • João Conde, Ricardo Moreira, João Torres, Pedro Cardoso, Hugo R. C. Ferreira, Marco O. P. Sampaio, João Tiago Ascensão, Pedro Bizarro

We propose a flexible system, Feature Monitoring (FM), that detects data drifts in such data sets, with a small and constant memory footprint and a small computational cost in streaming applications.

ConceptDistil: Model-Agnostic Distillation of Concept Explanations

no code implementations • 7 May 2022 • João Bento Sousa, Ricardo Moreira, Vladimir Balayan, Pedro Saleiro, Pedro Bizarro

Concept-based explanations aims to fill the model interpretability gap for non-technical humans-in-the-loop.

Explainable Models Knowledge Distillation +1

Data+Shift: Supporting visual investigation of data distribution shifts by data scientists

no code implementations • 29 Apr 2022 • João Palmeiro, Beatriz Malveiro, Rita Costa, David Polido, Ricardo Moreira, Pedro Bizarro

We propose Data+Shift, a visual analytics tool to support data scientists in the task of investigating the underlying factors of shift in data features in the context of fraud detection.

BIG-bench Machine Learning Fraud Detection