Christophe Gonzales

Decision making with multiple objectives using GAI networks

This paper deals with preference representation on combinatorial domains and preference-based recommendation in the context of multicriteria or multiagent decision making. The alternatives of the decision problem are seen as elements of a product set of attributes and preferences over solutions are represented by generalized additive decomposable (GAI) utility functions modeling individual preferences or criteria. Thanks to decomposability, utility vectors attached to solutions can be compiled into a graphical structure closely related to junction trees, the so-called GAI network. Using this structure, we present preference-based search algorithms for multicriteria or multiagent decision making. Although such models are often non-decomposable over attributes, we actually show that GAI networks are still useful to determine the most preferred alternatives provided preferences are compatible with Pareto dominance. We first present two algorithms for the determination of Pareto-optimal elements. Then the second of these algorithms is adapted so as to directly focus on the preferred solutions. We also provide results of numerical tests showing the practical efficiency of our procedures in various contexts such as compromise search and fair optimization in multicriteria or multiagent problems.

Choquet Optimization Using GAI Networks for Multiagent/Multicriteria Decision-Making

This paper is devoted to preference-based recommendation or configuration in the context of multiagent (or multicriteria) decision making. More precisely, we study the use of decomposable utility functions in the search for Choquet-optimal solutions on combinatorial domains. We consider problems where the alternatives (feasible solutions) are represented as elements of a product set of finite domains and evaluated according to different points of view (agents or criteria) leading to different objectives. Assuming that objectives take the form of GAI-utility functions over attributes, we investigate the use of GAI networks to determine efficiently an element maximizing an overall utility function defined by a Choquet integral.

Graph Structures for Knowledge Representation and Reasoning

Versatile and effective techniques for knowledge representation and reasoning (KRR) are essential for the development of successful intelligent systems. Many representatives of next generation KRR systems are based on graph-based knowledge representation formalisms and leverage graph-theoretical notions and results. The goal of the workshop series on Graph Structures for Knowledge Representation and Reasoning (GKR) is to bring together the researchers involved in the development and application of graph-based knowledge representation formalisms and reasoning techniques. This volume contains revised selected papers of the third edition of GKR, which took place in Beijing, China on August 3, 2013. Like the previous editions, held in Pasadena, USA (2009), and in Barcelona, Spain (2011), the workshop was associated with IJCAI (the International Joint Conference on Artificial Intelligence), thus providing the perfect venue for a rich and valuable exchange. The scientific program of this workshop included many topics related to graph-based knowledge representation and reasoning such as representations of constraint satisfaction problems, formal concept analysis, conceptual graphs, argumentation frameworks and many more. All in all, the third edition of the GKR workshop was very successful. The papers coming from diverse fields all addressed various issues for knowledge representation and reasoning and the common graph-theoretic background allowed to bridge the gap between the different communities. This made it possible for the participants to gain new insights and inspiration. We are grateful for the support of IJCAI and we would also like to thank the Program Committee of the workshop for their hard work in reviewing papers and providing valuable guidance to the contributors. But, of course, GKR 2013 would not have been possible without the dedicated involvement of the contributing authors and participants.

Speeding-up Structured Probabilistic Inference using Pattern Mining

In many domains where experts are the main source of knowledge, e.g., in reliability and risk management, a framework well suited for modeling, maintenance and exploitation of complex probabilistic systems is essential. In these domains, models usually define closed-world systems and result from the aggregation of multiple patterns repeated many times. Object Oriented-based Frameworks such as Probabilistic Relational Models (PRM) thus offer an effective way to represent such systems. They define patterns as classes and substitute large Bayesian networks (BN) by graphs of instances of these classes. In this framework, Structured Inference avoids many computation redundancies by exploiting class knowledge, hence reducing BN inference times by orders of magnitude. However, to keep modeling and maintenance costs low, object oriented-based framework’s classes often encode only generic situations. More complex situations, even those repeated many times, are only represented by combinations of instances. In this paper, we propose to determine online such combination patterns and exploit them as classes to speed-up Structured Inference. We prove that determining an optimal set of patterns is NP-hard. We also provide an efficient algorithm to approximate this set and show numerical experiments that highlight its practical efficiency.

Hierarchical Annealed Particle Swarm Optimization for Articulated Object Tracking

In this paper, we propose a novel algorithm for articulated object tracking, based on a hierarchical search and particle swarm optimization. Our approach aims to reduce the complexity induced by the high dimensional state space in articulated object tracking by decomposing the search space into subspaces and then using particle swarms to optimize over these subspaces hierarchically. Moreover, the intelligent search strategy proposed in [20] is integrated into each optimization step to provide a robust tracking algorithm under noisy observation conditions. Our quantitative and qualitative analysis both on synthetic and real video sequences show the efficiency of the proposed approach compared to other existing competitive tracking methods.

Patterns discovery for efficient structured probabilistic inference

In many domains where experts are the main source of knowledge, e.g., in reliability and risk management, a framework well suited for modeling, maintenance and exploitation of complex probabilistic systems is essential. In these domains, models usually define closed-world systems and result from the aggregation of multiple patterns repeated many times. Object Oriented-based Frameworks (OOF) such as Probabilistic Relational Models thus offer an effective way to represent such systems. OOFs define patterns as classes and substitute large Bayesian networks (BN) by graphs of instances of these classes. In this framework, Structured Inference avoids many computation redundancies by exploiting class knowledge, hence reducing BN inference times by orders of magnitude. However, to keep modeling and maintenance costs low, OOF classes often encode only generic situations. More complex situations, even those repeated many times, are only represented by combinations of instances. In this paper, we propose to determine such combination patterns and exploit them as classes to speed-up Structured Inference. We prove that determining an optimal set of patterns is NP-hard. We also provide an efficient algorithm to approximate this set and show numerical experiments that highlight its practical efficiency.

Réseaux GAI pour la prise de décision

Cet article traite de lelicitation de preferences et de la recommandation (choix et rangement) dans le contexte de la theorie de lutilite de multi-attribut. Nous nous concentrons sur le modele des utilites GAI decomposables (additivite generalisee) qui permet des interactions entre les attributs tout en preservant une certaine decomposabilite du modele. Nous presentons dabord une procedure systematique delicitation pour de telles fonctions dutilite. Cette procedure se fonde sur un modele graphique nomme reseau GAI qui est employe pour representer et gerer des independances entre attributs. Nous proposons ensuite un algorithme de choix et de rangement fonde sur les reseaux GAI pour resoudre efficacement aussi bien des problemes doptimisation que des problemes de rangement sur un produit cartesien. Nous montrons que les reseaux GAI peuvent a la fois integrer des contraintes et des preferences et donc etre efficacement utilises pour calculer le choix optimal et le rangement sous contraintes. Nous fournissons enfin des resultats dexperimentations numeriques qui montrent lefficacite de notre approche.

On a simple method for testing independencies in Bayesian networks: Testing Independencies in Bayesian Networks

Testing independencies is a fundamental task in reasoning with Bayesian networks (BNs). In practice, d‐separation is often used for this task, since it has linear‐time complexity. However, many have had difficulties understanding d‐separation in BNs. An equivalent method that is easier to understand, called m‐separation, transforms the problem from directed separation in BNs into classical separation in undirected graphs. Two main steps of this transformation are pruning the BN and adding undirected edges.

An empirical study of testing independencies in Bayesian networks using rp-separation

Abstract Directed separation (d-separation) played a fundamental role in the founding of Bayesian networks (BNs) and continues to be useful today in a wide range of applications. Given an independence to be tested, current implementations of d-separation explore the active part of a BN. On the other hand, an overlooked property of d-separation implies that d-separation need only consider the relevant part of a BN. We propose a new method for testing independencies in BNs, called relevant path separation (rp-separation), which explores the intersection between the active and relevant parts of a BN. Favourable experimental results are reported.

A Simple Method for Testing Independencies in Bayesian Networks

Testing independencies is a fundamental task in reasoning with Bayesian networks BNs. In practice, d-separation is often utilized for this task, since it has linear-time complexity. However, many have had difficulties in understanding d-separation in BNs. An equivalent method that is easier to understand, called m-separation, transforms the problem from directed separation in BNs into classical separation in undirected graphs. Two main steps of this transformation are pruning the BN and adding undirected edges. n nIn this paper, we propose u-separation as an even simpler method for testing independencies in a BN. Our approach also converts the problem into classical separation in an undirected graph. However, our method is based upon the novel concepts of inaugural variables and rationalization. Thereby, the primary advantage of u-separation over m-separation is that m-separation can prune unnecessarily and add superfluous edges. Hence, u-separation is a simpler method in this respect.