Séminaires

Date: Mardi 16 Juin 2026, 11h00 Lieu: salle C057 Title: FedStaleAsync: Efficiently Reusing Historical Updates to Enhance Asynchronous Federated Learning _________________________________________________________ Résumé : Federated learning (FL) enables clients to collaboratively train a shared model without exchanging local data. While asynchronous federated learning (AFL) improves training efficiency under high device heterogeneity by removing the synchronization bottlenecks of standard FL, it introduces stale updates and may exacerbate participation imbalance among heterogeneous clients. To mitigate this issue, prior work has proposed reusing historical updates to increase the contribution of slower clients. We theoretically show that existing AFL methods relying on this mechanism tend to underutilize newly received updates, placing excessive emphasis on increasingly stale information. Although strictly unbiased aggregation can correct this issue, it often incurs a substantial increase in variance. To address this trade-off, we propose FedStaleAsync, a principled weakly unbiased aggregation method that better exploits newly transmitted updates without significantly increasing variance. Experiments across diverse heterogeneous settings demonstrate that FedStaleAsync consistently outperforms existing asynchronous methods, achieving faster convergence and higher final accuracy. _________________________________________________________

Date: 22 Mai 2026, 11h30 Lieu: Salle C057 Titre: Repeated Multi-Resource Proportional Allocation Auction Games Résumé : In the multi-resource Kelly mechanism, players obtain a share of each resource in proportion to the bids they place on it. They thus engage in a non-cooperative game where they distribute their budgets across multiple resources. In this paper, we study the repeated variant of this game under standard no-regret algorithms, namely Online Gradient Descent (OGD) and Dual Averaging (DA) algorithms. More specifically, we investigate an additive utility framework with heterogeneous valuations across resources, where each resource-specific utility can be either logarithmic or linear. In this setting, we prove uniqueness of the Nash equilibrium. Moreover, we prove convergence of OGD and DA in the repeated game to this unique Nash Equilibrium. Extensive numerical simulations validate the theoretical results and measure convergence speed across different settings.

TITRE: Désambiguïsation sémantique d’ontologie par LLM Date: 29 Avril 2026, 11h30 Lieu: C057 Résumé : Je présenterais dans ce séminaire les travaux réalisés l’an dernier par Anastasiia Ribova. Je présenterais une approche qui explore le potentiel des grands modèles de langage (LLM) pour automatiser la validation et l’enrichissement d’ontologies et de graphes de connaissances. À partir d’un prompt simple et en exploitant des modèles de langage de taille intermédiaire, nous avons expérimenté plusieurs stratégies, notamment l’apprentissage zero-shot, le few-shot, le raisonnement par chaîne de pensée (CoT) et le décodage par auto-cohérence (SC). Notre méthode d’ensemble a systématiquement surpassé tous les modèles individuels sur deux domaines distincts de l’ontologie. Les résultats soulignent la capacité des LLM à opérer des distinctions nuancées et à évaluer les relations dérivées de l’ontologie avec un haut niveau de précision.

Date: 20/03/2026 à 11h30 Lieu: Salle C057 Titre: Learning in Proportional Allocation Auctions Games Résumé : The Kelly or proportional allocation mechanism is a simple and efficient auction-based scheme that distributes an infinitely divisible resource proportionally to the agents’ bids. When agents are aware of the allocation rule, their interactions form a game, that has been extensively studied. This paper examines the less explored repeated Kelly game, focusing mainly on utilities that are logarithmic in the allocated resource fraction. We first derive this logarithmic form from fairness–throughput trade-offs in wireless network slicing, and then prove that the induced stage game admits a unique Nash equilibrium (NE). For the repeated play, we prove convergence to this NE under three behavioral models: (i) all agents use Online Gradient Descent (OGD), (ii) all agents use Dual Averaging with a quadratic regularizer (DAQ) (a variant of the Follow-the-Regularized leader algorithm), and (iii) all agents play myopic best responses (BR). Our convergence results hold even when agents use personalized learning rates in OGD and DAQ (e.g., tuned to optimize individual regret bounds), and they extend to a broader class of utilities that meet a certain sufficient condition. Finally, we complement our theoretical results with extensive Plus d'infos

Vendredi 27 Février à 11h30 en C057. Title: Games with Rational and Herding Players Résumé : This talk examines large-population games with heterogeneous decision-making, in which an α-fraction of players are rational, while the remaining agents exhibit herding behaviour. We introduce a new equilibrium notion, called the α-Rational Nash Equilibrium (α-RNE), and discuss its interpretations. We show that some classical equilibria may disappear and new ones may emerge for small values of α>0. Interestingly, rational players benefit from the presence of herding and may even achieve utility exceeding the socially optimum. Even more strikingly, in some cases, herding players also benefit, attaining utility close to the social optimum. Using transportation and bandwidth sharing games as case studies, we analyse the impact of herding on congestion and resource allocation, and quantify system inefficiencies through the Price of Anarchy. Finally, we discuss the mechanism and influence design in the presence of herding. While the expanded set of equilibria creates new opportunities, it also increases the risk of undesirable outcomes when influence cannot be effectively implemented.