arXiv:2512.00545v1 Announce Type: cross 
Abstract: The Influence Maximization (IM) problem aims to select a set of seed nodes within a given budget to maximize the spread of influence in a social network. However, real-world social networks have several structural inequalities, such as dominant majority groups and underrepresented minority groups. If these inequalities are not considered while designing IM algorithms, the outcomes might be biased, disproportionately benefiting majority groups while marginalizing minorities. In this work, we address this gap by designing a fairness-aware IM method using Reinforcement Learning (RL) that ensures equitable influence outreach across all communities, regardless of protected attributes. Fairness is incorporated using a maximin fairness objective, which prioritizes improving the outreach of the least-influenced group, pushing the solution toward an equitable influence distribution. We propose a novel fairness-aware deep RL method, called DQ4FairIM, that maximizes the expected number of influenced nodes by learning an RL policy. The learnt policy ensures that minority groups formulate the IM problem as a Markov Decision Process (MDP) and use deep Q-learning, combined with the Structure2Vec network embedding, earning together with Structure2Vec network embedding to solve the MDP. We perform extensive experiments on synthetic benchmarks and real-world networks to compare our method with fairness-agnostic and fairness-aware baselines. The results show that our method achieves a higher level of fairness while maintaining a better fairness-performance trade-off than baselines. Additionally, our approach learns effective seeding policies that generalize across problem instances without retraining, such as varying the network size or the number of seed nodes.

التطور الأخير لـ DQ4FairIM يقدم نهجًا واعيًا للعدالة في مشكلة تعظيم التأثير (IM) باستخدام التعلم المعزز العميق (RL). تهدف هذه الطريقة إلى اختيار عقدة البذور ضمن ميزانية معينة لتعظيم انتشار التأثير في الشبكات الاجتماعية، مع معالجة عدم المساواة الهيكلية التي غالبًا ما تفضل المجموعات الكبرى على الأقليات.

El reciente desarrollo de DQ4FairIM introduce un enfoque consciente de la equidad para la Maximización de Influencia (IM) utilizando Aprendizaje por Refuerzo (RL) profundo. Este método tiene como objetivo seleccionar nodos semilla dentro de un presupuesto para maximizar la difusión de influencia en redes sociales, abordando las desigualdades estructurales que a menudo favorecen a los grupos mayoritarios sobre las minorías.

Le développement récent de DQ4FairIM introduit une approche consciente de l'équité pour la maximisation de l'influence (IM) en utilisant l'apprentissage par renforcement (RL) profond. Cette méthode vise à sélectionner des nœuds semences dans un budget pour maximiser la diffusion de l'influence dans les réseaux sociaux tout en abordant les inégalités structurelles qui favorisent souvent les groupes majoritaires au détriment des minorités.

The recent development of DQ4FairIM introduces a fairness-aware approach to Influence Maximization (IM) using Deep Reinforcement Learning (RL). This method aims to select seed nodes within a budget to maximize influence spread in social networks while addressing structural inequalities that often favor majority groups over minorities.

DQ4FairIM: Fairness-aware Influence Maximization using Deep Reinforcement Learning

arXiv:2502.03492v2 Announce Type: replace 
Abstract: Teaching large language models (LLMs) to critique and refine their outputs is crucial for building systems that can iteratively improve, yet it is fundamentally limited by the ability to provide accurate judgments and actionable suggestions. In this work, we study LLM critics for code generation and propose $\texttt{CTRL}$, a framework for $\texttt{C}$ritic $\texttt{T}$raining via $\texttt{R}$einforcement $\texttt{L}$earning, which trains a critic model to generate feedback that maximizes correction performance for a fixed generator model without human supervision. Our results demonstrate that critics trained with $\texttt{CTRL}$ significantly enhance pass rates and mitigate compounding errors across both base and stronger generator models. Furthermore, we show that these critic models act as accurate generative reward models and enable test-time scaling through iterative critique-revision, achieving up to 106.1% relative improvements across challenging code generation benchmarks.

تم تطوير إطار عمل جديد يسمى CTRL لتعليم نماذج اللغة الكبيرة (LLMs) كيفية نقد وتحسين مخرجاتها من خلال التعلم المعزز. تتيح هذه الطريقة لنماذج النقد إنتاج تعليقات تعزز أداء نماذج التوليد دون تدخل بشري، مما يؤدي إلى تحسين معدلات النجاح وتقليل الأخطاء في مهام توليد الشيفرة.

Se ha desarrollado un nuevo marco llamado CTRL para enseñar a los grandes modelos de lenguaje (LLMs) a criticar y refinar sus resultados a través del aprendizaje por refuerzo. Este enfoque permite que los modelos críticos generen retroalimentación que mejora el rendimiento de los modelos generadores sin intervención humana, lo que lleva a tasas de aprobación mejoradas y a una reducción de errores en tareas de generación de código.

Un nouveau cadre appelé CTRL a été développé pour enseigner aux grands modèles de langage (LLMs) à critiquer et à affiner leurs résultats grâce à l'apprentissage par renforcement. Cette approche permet aux modèles critiques de générer des retours qui améliorent les performances des modèles générateurs sans intervention humaine, conduisant à des taux de réussite améliorés et à une réduction des erreurs dans les tâches de génération de code.

A new framework called CTRL has been developed to teach large language models (LLMs) to critique and refine their outputs through reinforcement learning. This approach allows critic models to generate feedback that enhances the performance of generator models without human intervention, leading to improved pass rates and reduced errors in code generation tasks.

DQ4FairIM: Fairness-aware Influence Maximization using Deep Reinforcement Learning

Was this article worth reading? Share it

AINF Membership

DiveDeck.AI

Pmfm