Author name cluster

Laurence Rozé

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

ECAI Conference 2025 Conference Paper

Plausible Conditional Generation-Based Counterfactual Explanations for Multivariate Times Series Classification

Paul Sevellec
Elisa Fromont
Romaric Gaudel
Laurence Rozé
Matteo Sammarco

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 post-hoc analyzes of classification models. We introduce CFE4MTS (CounterFactual Explanation for Multivariate Time Series), a conditional, generation-based, plausible counterfactual explanation method, specifically designed for multivariate time series classification. Our approach leverages 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 the state of the art methods.

Details

AAAI Conference 2024 Conference Paper

Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selection

Gwladys Kelodjou
Laurence Rozé
Véronique Masson
Luis Galárraga
Romaric Gaudel
Maurice Tchuente
Alexandre Termier

Machine learning techniques, such as deep learning and ensemble methods, are widely used in various domains due to their ability to handle complex real-world tasks. However, their black-box nature has raised multiple concerns about the fairness, trustworthiness, and transparency of computer-assisted decision-making. This has led to the emergence of local post-hoc explainability methods, which offer explanations for individual decisions made by black-box algorithms. Among these methods, Kernel SHAP is widely used due to its model-agnostic nature and its well-founded theoretical framework. Despite these strengths, Kernel SHAP suffers from high instability: different executions of the method with the same inputs can lead to significantly different explanations, which diminishes the relevance of the explanations. The contribution of this paper is two-fold. On the one hand, we show that Kernel SHAP's instability is caused by its stochastic neighbor selection procedure, which we adapt to achieve full stability without compromising explanation fidelity. On the other hand, we show that by restricting the neighbors generation to perturbations of size 1 -- which we call the coalitions of Layer 1 -- we obtain a novel feature-attribution method that is fully stable, computationally efficient, and still meaningful.

PDF Details DOI

AAAI Conference 2022 Conference Paper

TAG: Learning Timed Automata from Logs

Lénaïg Cornanguer
Christine Largouët
Laurence Rozé
Alexandre Termier

Event logs are often one of the main sources of information to understand the behavior of a system. While numerous approaches have extracted partial information from event logs, in this work, we aim at inferring a global model of a system from its event logs. We consider real-time systems, which can be modeled with Timed Automata: our approach is thus a Timed Automata learner. There is a handful of related work, however, they might require a lot of parameters or produce Timed Automata that either are undeterministic or lack precision. In contrast, our proposed approach, called TAG, requires only one parameter and learns a deterministic Timed Automaton having a good tradeoff between accuracy and complexity of the automata. This allows getting an interpretable and accurate global model of the real-time system considered. Our experiments compare our approach to the related work and demonstrate its merits.

PDF Details

ECAI Conference 2008 Conference Paper

Chronicles for On-line Diagnosis of Distributed Systems

Xavier Le Guillou
Marie-Odile Cordier
Sophie Robin
Laurence Rozé

The formalism of chronicles has been proposed to monitor and diagnose dynamic physical systems. Even if efficient chronicle recognition algorithms exist, it is now well-known that distributed approaches are better suited to monitor real systems. In this article, we adapt the chronicle-based approach to a distributed context and illustrate this work on the monitoring of software components.

Details

LOPSTR Conference 2000 Conference Paper

Proof Obligations of the B Formal Method: Local Proofs Ensure Global Consistency

Mireille Ducassé
Laurence Rozé

Abstract The B formal method has been successfully used in large projects and is not reserved to experts. The main correctness criterion of B is that every piece of code must preserve invariant properties. In this article, we briefly introduce the basic notions of B. We then concentrate on the proof obligations. After introducing them, we show how the sum of local proofs makes a global consistency. We believe that this strong modularity is essential for the tractability of the proofs.

Details