Author name cluster

Steve Bellart

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.

4 papers

1 author row

IJCAI Conference 2023 Conference Paper

Computing Abductive Explanations for Boosted Regression Trees

Gilles Audemard
Steve Bellart
Jean-Marie Lagniez
Pierre Marquis

We present two algorithms for generating (resp. evaluating) abductive explanations for boosted regression trees. Given an instance x and an interval I containing its value F (x) for the boosted regression tree F at hand, the generation algorithm returns a (most general) term t over the Boolean conditions in F such that every instance x′ satisfying t is such that F (x′ ) ∈ I. The evaluation algorithm tackles the corresponding inverse problem: given F, x and a term t over the Boolean conditions in F such that t covers x, find the least interval I_t such that for every instance x′ covered by t we have F (x′ ) ∈ I_t. Experiments on various datasets show that the two algorithms are practical enough to be used for generating (resp. evaluating) abductive explanations for boosted regression trees based on a large number of Boolean conditions.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

On Preferred Abductive Explanations for Decision Trees and Random Forests

Gilles Audemard
Steve Bellart
Louenas Bounia
Frederic Koriche
Jean-Marie Lagniez
Pierre Marquis

Abductive explanations take a central place in eXplainable Artificial Intelligence (XAI) by clarifying with few features the way data instances are classified. However, instances may have exponentially many minimum-size abductive explanations, and this source of complexity holds even for ``intelligible'' classifiers, such as decision trees. When the number of such abductive explanations is huge, computing one of them, only, is often not informative enough. Especially, better explanations than the one that is derived may exist. As a way to circumvent this issue, we propose to leverage a model of the explainee, making precise her / his preferences about explanations, and to compute only preferred explanations. In this paper, several models are pointed out and discussed. For each model, we present and evaluate an algorithm for computing preferred majoritary reasons, where majoritary reasons are specific abductive explanations suited to random forests. We show that in practice the preferred majoritary reasons for an instance can be far less numerous than its majoritary reasons.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Trading Complexity for Sparsity in Random Forest Explanations

Gilles Audemard
Steve Bellart
Louènas Bounia
Frédéric Koriche
Jean-Marie Lagniez
Pierre Marquis

Random forests have long been considered as powerful model ensembles in machine learning. By training multiple decision trees, whose diversity is fostered through data and feature subsampling, the resulting random forest can lead to more stable and reliable predictions than a single decision tree. This however comes at the cost of decreased interpretability: while decision trees are often easily interpretable, the predictions made by random forests are much more difficult to understand, as they involve a majority vote over multiple decision trees. In this paper, we examine different types of reasons that explain “why” an input instance is classified as positive or negative by a Boolean random forest. Notably, as an alternative to prime-implicant explanations taking the form of subset-minimal implicants of the random forest, we introduce majoritary reasons which are subset-minimal implicants of a strict majority of decision trees. For these abductive explanations, the tractability of the generation problem (finding one reason) and the optimization problem (finding one minimumsized reason) are investigated. Unlike prime-implicant explanations, majoritary reasons may contain redundant features. However, in practice, prime-implicant explanations for which the identification problem is DP-complete - are slightly larger than majoritary reasons that can be generated using a simple linear-time greedy algorithm. They are also significantly larger than minimum-sized majoritary reasons which can be approached using an anytime PARTIAL MAXSAT algorithm.

PDF Details

KR Conference 2021 Conference Paper

On the Computational Intelligibility of Boolean Classifiers

Gilles Audemard
Steve Bellart
Louenas Bounia
Frédéric Koriche
Jean-Marie Lagniez
Pierre Marquis

In this paper, we investigate the computational intelligibility of Boolean classifiers, characterized by their ability to answer XAI queries in polynomial time. The classifiers under consideration are decision trees, DNF formulae, decision lists, decision rules, tree ensembles, and Boolean neural nets. Using 9 XAI queries, including both explanation queries and verification queries, we show the existence of large intelligibility gap between the families of classifiers. On the one hand, all the 9 XAI queries are tractable for decision trees. On the other hand, none of them is tractable for DNF formulae, decision lists, random forests, boosted decision trees, Boolean multilayer perceptrons, and binarized neural networks.

PDF Details DOI