arXiv subjects

Marie-Jeanne Lesot

Publications and source records attributed to Marie-Jeanne Lesot.

26 records · Page 2Linked to original sources

arXiv2019

Issues with post-hoc counterfactual explanations: a discussion

Counterfactual post-hoc interpretability approaches have been proven to be useful tools to generate explanations for the predictions of a trained blackbox classifier. However, the assumptions they make about the data and the classifier make them unreliable in many contexts. In this paper, we discuss three desirable properties and approaches to quantify them: proximity, connectedness and stability. In addition, we illustrate that there is a risk for post-hoc counterfactual approaches to not satisfy these properties.

cs.LG↗

arXiv2019

ROHSA: Regularized Optimization for Hyper-Spectral Analysis - Application to phase separation of 21 cm data

Extracting the multiphase structure of the neutral interstellar medium (ISM) is key to understand the star formation in galaxies. The radiative condensation of the diffuse warm neutral medium producing a thermally unstable lukewarm medium and a dense cold medium is closely related to the initial step which leads the HI-to-H2 transition and the formation of molecular clouds. Up to now the mapping of these phases out of 21 cm emission hyper-spectral cubes has remained elusive mostly due to the velocity blending of individual cold structures present on a given line of sight. To address this problem, we developed a new Gaussian decomposition algorithm named ROHSA (Regularized Optimization for Hyper-Spectral Analysis) based on a multi-resolution process from coarse to fine grid. ROHSA uses a regularized non-linear least-square criterion to take into account simultaneously the spatial coherence of the emission and the multiphase nature of the gas. In order to obtain a solution with spatially smooth parameters, the optimization is performed on the whole data cube at once. The performances of ROHSA were tested on a synthetic observation computed from numerical simulations of thermally bi-stable turbulence. An application on a 21 cm observation of a high Galactic latitude region from the GHIGLS survey is presented. The evaluation of ROHSA on synthetic 21 cm observations shows that it is able to recover the multiphase nature of the HI and physically meaningful information about the underlying three-dimensional fields (density, velocity and temperature). The application on a real 21 cm observation of a high Galactic latitude field produces a picture of the multiphase HI, with isolated, filamentary and narrow structures and wider, diffuse and space filling components. The test-case field used here contains significant intermediate-velocity clouds that were well mapped out by the algorithm.

astro-ph.GA↗

arXiv2018

Detecting Potential Local Adversarial Examples for Human-Interpretable Defense

Machine learning models are increasingly used in the industry to make decisions such as credit insurance approval. Some people may be tempted to manipulate specific variables, such as the age or the salary, in order to get better chances of approval. In this ongoing work, we propose to discuss, with a first proposition, the issue of detecting a potential local adversarial example on classical tabular data by providing to a human expert the locally critical features for the classifier's decision, in order to control the provided information and avoid a fraud.

stat.ML↗

arXiv2018

Defining Locality for Surrogates in Post-hoc Interpretablity

Local surrogate models, to approximate the local decision boundary of a black-box classifier, constitute one approach to generate explanations for the rationale behind an individual prediction made by the back-box. This paper highlights the importance of defining the right locality, the neighborhood on which a local surrogate is trained, in order to approximate accurately the local black-box decision boundary. Unfortunately, as shown in this paper, this issue is not only a parameter or sampling distribution challenge and has a major impact on the relevance and quality of the approximation of the local black-box decision boundary and thus on the meaning and accuracy of the generated explanation. To overcome the identified problems, quantified with an adapted measure and procedure, we propose to generate surrogate-based explanations for individual predictions based on a sampling centered on particular place of the decision boundary, relevant for the prediction to be explained, rather than on the prediction itself as it is classically done. We evaluate the novel approach compared to state-of-the-art methods and a straightforward improvement thereof on four UCI datasets.

cs.LG↗

arXiv2017

Inverse Classification for Comparison-based Interpretability in Machine Learning

In the context of post-hoc interpretability, this paper addresses the task of explaining the prediction of a classifier, considering the case where no information is available, neither on the classifier itself, nor on the processed data (neither the training nor the test data). It proposes an instance-based approach whose principle consists in determining the minimal changes needed to alter a prediction: given a data point whose classification must be explained, the proposed method consists in identifying a close neighbour classified differently, where the closeness definition integrates a sparsity constraint. This principle is implemented using observation generation in the Growing Spheres algorithm. Experimental results on two datasets illustrate the relevance of the proposed approach that can be used to gain knowledge about the classifier.

stat.ML↗

arXiv2017

Overlapping Community Detection by Local Decentralised Vertex-centred Process

This paper focuses on the identification of overlapping communities, allowing nodes to simultaneously belong to several communities, in a decentralised way. To that aim it proposes LOCNeSs, an algorithm specially designed to run in a decentralised environment and to limit propagation, two essential characteristics to be applied in mobile networks. It is based on the exploitation of the preferential attachment mechanism in networks. Experimental results show that LOCNeSs is stable and achieves good overlapping vertex identification.

cs.SI↗

arXiv2016

Vertex-centred Method to Detect Communities in Evolving Networks

Finding communities in evolving networks is a difficult task and raises issues different from the classic static detection case. We introduce an approach based on the recent vertex-centred paradigm. The proposed algorithm, named DynLOCNeSs, detects communities by scanning and evaluating each vertex neighbourhood, which can be done independently in a parallel way. It is done by means of a preference measure, using these preferences to handle community changes. We also introduce a new vertex neighbourhood preference measure, CWCN, more efficient than current existing ones in the considered context. Experimental results show the relevance of this measure and the ability of the proposed approach to detect classical community evolution patterns such as grow-shrink and merge-split.

cs.SI↗

arXiv2015

Fast community structure local uncovering by independent vertex-centred process

This paper addresses the task of community detection and proposes a local approach based on a distributed list building, where each vertex broadcasts basic information that only depends on its degree and that of its neighbours. A decentralised external process then unveils the community structure. The relevance of the proposed method is experimentally shown on both artificial and real data.

cs.SI↗