Elisa Fromont
Research Subjects
Elisa Fromont has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Laurence Rozé1 shared publication
- Matteo Sammarco
Stellantis
1 shared publication - Paul Sevellec1 shared publication
- Romaric Gaudel
UMR 9189 Univ. Lille CNRS F-59000 Centrale Lille Lille CRIStAL France
1 shared publication
Latest Publications
- Open Access
Plausible Generation-based Counterfactual Explanations for Multivariate Times Series Classification
Multivariate time series (MTS) are prevalent but inherently complex, making them challenging to analyze due to strong temporal and inter-variable correlations. This complexity often results in the use of sophisticated and difficult-to-interpret machine learning models. In real-life scenarios where critical applications of these models are common, their acceptability is crucial. Counterfactual explanations have emerged as a valuable tool for understanding machine learning systems by providing posthoc analyzes of classification models. We introduce CFE4MTS (CounterFactual Explanation for Multivariate Time Series), a generation-based plausible counterfactual explanation method specifically designed for multivariate time series classification. Our approach utilizes advanced time series modeling techniques to generate interpretable counterfactuals that belong to a given target class distribution. To evaluate the effectiveness of our method, we apply it to various real datasets, demonstrating the superiority of our approach over several state-of-the-art generative approaches.
Open AccessPlausible Generation-based Counterfactual Explanations for Multivariate Times Series Classification
Multivariate time series (MTS) are prevalent but inherently complex, making them challenging to analyze due to strong temporal and inter-variable correlations. This complexity often results in the use of sophisticated and difficult-to-interpret machine learning models. In real-life scenarios where critical applications of these models are common, their acceptability is crucial. Counterfactual explanations have emerged as a valuable tool for understanding machine learning systems by providing posthoc analyzes of classification models. We introduce CFE4MTS (CounterFactual Explanation for Multivariate Time Series), a generation-based plausible counterfactual explanation method specifically designed for multivariate time series classification. Our approach utilizes advanced time series modeling techniques to generate interpretable counterfactuals that belong to a given target class distribution. To evaluate the effectiveness of our method, we apply it to various real datasets, demonstrating the superiority of our approach over several state-of-the-art generative approaches.