Author name cluster

Christophe Labreuche

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.

14 papers

2 author rows

ECAI Conference 2025 Conference Paper

Enhancing CBBA Convergence and Optimality Guarantees in Multiagent Task Allocation

Alexandre Kha
Aurélie Beynier
Christophe Labreuche
Mathieu Marchand

The Consensus-Based Bundle Algorithm (CBBA) is a leading approach for decentralized task allocation, offering conflict-free task assignments within a bounded number of iterations and a 50% optimality guarantee for utility functions with Diminishing Marginal Gains (DMG). However, we identify three limitations: (1) the Time-Discounted Reward utility function proposed with CBBA is not always DMG, (2) the optimality guarantee may not hold even with DMG functions, and (3) the algorithm can be inefficient as it incurs unnecessary idle iterations after convergence. To address these issues, we propose three key contributions. For limitation (1), we introduce the Repeated Path Times utility function, which is DMG in all cases and aligns with Min-Sum and Makespan objectives. Regarding point (2), we develop Global CBBA (GCBBA), a variant algorithm that leverages global consensus to restore the 50% optimality guarantee under DMG and ensures bounded convergence for any bundle-monotonic objective. Finally, to address limitation (3), we design a decentralized early convergence detection method to improve efficiency. Experimental results show that GCBBA significantly accelerates convergence on large-scale problems compared to the baseline CBBA.

Details

ICLR Conference 2025 Conference Paper

Provably Safeguarding a Classifier from OOD and Adversarial Samples

Nicolas Atienza
Johanne Cohen
Christophe Labreuche
Michèle Sebag

This paper aims to transform a trained classifier into an abstaining classifier, such that the latter is provably protected from out-of-distribution and adversarial samples. The proposed Sample-efficient Probabilistic Detection using Extreme Value Theory (SPADE) approach relies on a Generalized Extreme Value (GEV) model of the training distribution in the latent space of the classifier. Under mild assumptions, this GEV model allows for formally characterizing out-of-distribution and adversarial samples and rejecting them. Empirical validation of the approach is conducted on various neural architectures (ResNet, VGG, and Vision Transformer) and considers medium and large-sized datasets (CIFAR-10, CIFAR-100, and ImageNet). The results show the stability and frugality of the GEV model and demonstrate SPADE’s efficiency compared to the state-of-the-art methods.

Details

IJCAI Conference 2024 Conference Paper

Cutting the Black Box: Conceptual Interpretation of a Deep Neural Net with Multi-Modal Embeddings and Multi-Criteria Decision Aid

Nicolas Atienza
Roman Bresson
Cyriaque Rousselot
Philippe Caillou
Johanne Cohen
Christophe Labreuche
Michele Sebag

This paper tackles the concept-based explanation of neural models in computer vision, building upon the state of the art in Multi-Criteria Decision Aid (MCDA). The novelty of the approach is to leverage multi-modal embeddings from CLIP to bridge the gap between pixel-based and concept-based representations. The proposed Cut the Black Box (CB2) approach disentangles the latent representation of a trained pixel-based neural net, referred to as teacher model, along a 3-step process. Firstly, the pixel-based representation of the samples is mapped onto a conceptual representation using multi-modal embeddings. Secondly, an interpretable-by-design MCDA student model is trained by distillation from the teacher model, using the conceptual sample representation. Thirdly, the alignment of the teacher and student latent representations spells out the concepts relevant to explaining the teacher model. The empirical validation of the approach on ResNet, VGG, and VisionTransformer on Cifar-10, Cifar-100, Tiny ImageNet, and Fashion-MNIST showcases the effectiveness of the interpretations provided for the teacher models. The analysis reveals that decision-making predominantly relies on few concepts, thereby exposing potential bias in the teacher's decisions.

PDF Details DOI

KR Conference 2021 Conference Paper

On the Identifiability of Hierarchical Decision Models

Roman Bresson
Johanne Cohen
Eyke Hüllermeier
Christophe Labreuche
Michèle Sebag

Interpretability is a desirable property for machine learning and decision models, particularly in the context of safety-critical applications. Another most desirable property of the sought model is to be unique or {\em identifiable} in the considered class of models: the fact that the same functional dependency can be represented by a number of syntactically different models adversely affects the model interpretability, and prevents the expert from easily checking their validity. This paper focuses on the Choquet integral (CI) models and their hierarchical extensions (HCI). HCIs aim to support expert decision making, by gradually aggregating preferences based on criteria; they are widely used in multi-criteria decision aiding {and are receiving interest from the} Machine Learning {community}, as they preserve the high readability of CIs while efficiently scaling up w. r. t. the number of criteria. The main contribution is to establish the identifiability property of HCI under mild conditions: two HCIs implementing the same aggregation function on the criteria space necessarily have the same hierarchical structure and aggregation parameters. The identifiability property holds even when the marginal utility functions are learned from the data. This makes the class of HCI models a most appropriate choice in domains where the model interpretability and reliability are of primary concern.

PDF Details DOI

IJCAI Conference 2020 Conference Paper

Neural Representation and Learning of Hierarchical 2-additive Choquet Integrals

Roman Bresson
Johanne Cohen
Eyke Hüllermeier
Christophe Labreuche
Michèle Sebag

Multi-Criteria Decision Making (MCDM) aims at modelling expert preferences and assisting decision makers in identifying options best accommodating expert criteria. An instance of MCDM model, the Choquet integral is widely used in real-world applications, due to its ability to capture interactions between criteria while retaining interpretability. Aimed at a better scalability and modularity, hierarchical Choquet integrals involve intermediate aggregations of the interacting criteria, at the cost of a more complex elicitation. The paper presents a machine learning-based approach for the automatic identification of hierarchical MCDM models, composed of 2-additive Choquet integral aggregators and of marginal utility functions on the raw features from data reflecting expert preferences. The proposed NEUR-HCI framework relies on a specific neural architecture, enforcing by design the Choquet model constraints and supporting its end-to-end training. The empirical validation of NEUR-HCI on real-world and artificial benchmarks demonstrates the merits of the approach compared to state-of-art baselines.

PDF Details DOI

IJCAI Conference 2019 Conference Paper

Comparing Options with Argument Schemes Powered by Cancellation

Khaled Belahcene
Christophe Labreuche
Nicolas Maudet
Vincent Mousseau
Wassila Ouerdane

We introduce a way of reasoning about preferences represented as pairwise comparative statements, based on a very simple yet appealing principle: cancelling out common values across statements. We formalize and streamline this procedure with argument schemes. As a result, any conclusion drawn by means of this approach comes along with a justification. It turns out that the statements which can be inferred through this process form a proper preference relation. More precisely, it corresponds to a necessary preference relation under the assumption of additive utilities. We show the inference task can be performed in polynomial time in this setting, but that finding a minimal length explanation is NP-complete.

PDF Details

IJCAI Conference 2019 Conference Paper

How to Handle Missing Values in Multi-Criteria Decision Aiding?

Christophe Labreuche
Sébastien Destercke

It is often the case in the applications of Multi-Criteria Decision Making that the values of alternatives are unknown on some attributes. An interesting situation arises when the attributes having missing values are actually not relevant and shall thus be removed from the model. Given a model that has been elicited on the complete set of attributes, we are looking thus for a way -- called restriction operator -- to automatically remove the missing attributes from this model. Axiomatic characterizations are proposed for three classes of models. For general quantitative models, the restriction operator is characterized by linearity, recursivity and decomposition on variables. The second class is the set of monotone quantitative models satisfying normalization conditions. The linearity axiom is changed to fit with these conditions. Adding recursivity and symmetry, the restriction operator takes the form of a normalized average. For the last class of models -- namely the Choquet integral, we obtain a simpler expression. Finally, a very intuitive interpretation is provided.

PDF Details

IJCAI Conference 2018 Conference Paper

Accountable Approval Sorting

Khaled Belahcene
Yann Chevaleyre
Christophe Labreuche
Nicolas Maudet
Vincent Mousseau
Wassila Ouerdane

We consider decision situations in which a set of points of view (voters, criteria) are to sort a set of candidates to ordered categories (Good/Bad). Candidates are judged good, when approved by a sufficient set of points of view; this corresponds to NonCompensatory Sorting. To be accountable, such approval sorting should provide guarantees about the decision process and decisions concerning specific candidates. We formalize accountability using a feasibility problem expressed as a boolean satisfiability formulation. We illustrate different forms of accountability when a committee decides with approval sorting and study the information that should be disclosed by the committee.

PDF Details

IJCAI Conference 2018 Conference Paper

Explaining Multi-Criteria Decision Aiding Models with an Extended Shapley Value

Christophe Labreuche
Simon Fossier

The capability to explain the result of aggregation models to decision makers is key to reinforcing user trust. In practice, Multi-Criteria Decision Aiding models are often organized in a hierarchical way, based on a tree of criteria. We present an explanation approach usable with any hierarchical multi-criteria model, based on an influence index of each attribute on the decision. A set of desirable axioms are defined. We show that there is a unique index fulfilling these axioms. This new index is an extension of the Shapley value on trees. An efficient rewriting of this index, drastically reducing the computation time, is obtained. Finally, the use of the new index is illustrated on an example.

PDF Details

IJCAI Conference 2017 Conference Paper

A Model for Accountable Ordinal Sorting

Khaled Belahcene
Christophe Labreuche
Nicolas Maudet
Vincent Mousseau
Wassila Ouerdane

We address the problem of multicriteria ordinalsorting through the lens of accountability, i. e. theability of a human decision-maker to own a recommendationmade by the system. We put forward anumber of model features that would favor the capabilityto support the recommendation with a convincingexplanation. To account for that, we designa recommender system implementing and formalizingsuch features. This system outputs explanationsdefined under the form of specific argumentschemes tailored to represent the specific rules ofthe model. At the end, we discuss possible andpromising argumentative perspectives.

PDF Details

ECAI Conference 2012 Conference Paper

Justifying Dominating Options when Preferential Information is Incomplete

Christophe Labreuche
Nicolas Maudet
Wassila Ouerdane

Providing convincing explanations to accompany recommendations is a key issue in decision-aiding. In the context of decisions involving multiple criteria, the problem is made very difficult because the decision model itself may involve a complex process. In this paper, we investigate the following issue: when the preferential information provided by the user is incomplete, is there a principled way to define what is a "simple" explanation for a recommended choice? We argue first that explanations may necessitate different levels of detail. Next, we show that even when a detailed explanation is necessary, it is possible to distinguish explanations of different levels of complexity. Our results rely on an original connection we establish between the "mechanics" required to compute supporting coalitions of criteria and the simplicity of the explanation.

Details

AIJ Journal 2011 Journal Article

A general framework for explaining the results of a multi-attribute preference model

Christophe Labreuche

The automatic generation of an explanation of the prescription made by a multi-attribute decision model is crucial in many applications, such as recommender systems. This task is complex since the quantitative models are not designed to be easily explainable. The major limitation of the previous research is that there is no formal justification of the arguments that are selected in the explanation. The goal of this paper is to define a general framework to justify which arguments shall be selected, in the case where the decision model is based on weights assigned to the attributes. Due to the complexity of explaining a preference model based on utility theory, several explanation reasonings are necessary to cover all cases – ranging from situations where the prescription is trivial to situations where the prescription is much more tight. The set of selected arguments is, in this framework, a non-dominated element of a combinatorial structure in the sense of an order relation. Our general approach is instantiated precisely on three models: the probabilistic expected utility model, the qualitative pessimistic minmax model and the concordance rule, which are all constructed from a weight vector.

Details DOI

ECAI Conference 2010 Conference Paper

Preference-Based Argumentation Framework with Varied-Preference Intensity

Souhila Kaci
Christophe Labreuche

Recently, Dung's argumentation has been extended in order to consider the strength of the defeat relation, i. e. , to quantify the degree to which an argument defeats another one. We construct an argumentation framework with varied-strength defeats from a preference-based argumentation framework with an intensity degree in the preference relation. We also consider the case when the preference over the arguments is constructed from a valued logic.

Details

AAMAS Conference 2007 Conference Paper

A Multilateral Multi-issue Negotiation Protocol

Miniar Hemaissia
Amal El Fallah Seghrouchni
Christophe Labreuche
Juliette Mattioli

In this paper, we present a new protocol to address multilateral multi-issue negotiation in a cooperative context. We consider complex dependencies between multiple issues by modelling the preferences of the agents with a multi-criteria decision aid tool, also enabling us to extract relevant information on a proposal assessment. This information is used in the protocol to help in accelerating the search for a consensus between the cooperative agents. In addition, the negotiation procedure is defined in a crisis management context where the common objective of our agents is also considered in the preferences of a mediator agent.

PDF