arXiv:2510.21055v1 Announce Type: new 
Abstract: We study the online multi-class selection problem with group fairness guarantees, where limited resources must be allocated to sequentially arriving agents. Our work addresses two key limitations in the existing literature. First, we introduce a novel lossless rounding scheme that ensures the integral algorithm achieves the same expected performance as any fractional solution. Second, we explicitly address the challenges introduced by agents who belong to multiple classes. To this end, we develop a randomized algorithm based on a relax-and-round framework. The algorithm first computes a fractional solution using a resource reservation approach -- referred to as the set-aside mechanism -- to enforce fairness across classes. The subsequent rounding step preserves these fairness guarantees without degrading performance. Additionally, we propose a learning-augmented variant that incorporates untrusted machine-learned predictions to better balance fairness and efficiency in practical settings.

تم نشر دراسة جديدة حول اختيار الفئات المتعددة عبر الإنترنت مع ضمانات العدالة الجماعية، حيث تقدم حلولًا مبتكرة لتحسين تخصيص الموارد بين الوكلاء الذين يصلون بشكل متتابع. هذه البحث مهم لأنه يتناول القيود الحالية في العدالة والأداء، مما يضمن أن الخوارزمية يمكن أن تحقق نتائج مثالية دون المساس بالعدالة. من خلال تقديم مخطط تقريبي بدون خسائر، يعد البحث بتحسين فعالية توزيع الموارد، مما يجعله تقدمًا حاسمًا في هذا المجال.

Se ha publicado un nuevo estudio sobre la selección multi-clase en línea con garantías de equidad grupal, presentando soluciones innovadoras para mejorar la asignación de recursos entre agentes que llegan secuencialmente. Esta investigación es significativa ya que aborda las limitaciones existentes en equidad y rendimiento, asegurando que el algoritmo pueda lograr resultados óptimos sin comprometer la equidad. Al introducir un esquema de redondeo sin pérdidas, el estudio promete mejorar la efectividad de la distribución de recursos, convirtiéndose en un avance crucial en el campo.

Une nouvelle étude sur la sélection multi-classe en ligne avec des garanties d'équité de groupe a été publiée, présentant des solutions innovantes pour améliorer l'allocation des ressources parmi les agents arrivant séquentiellement. Cette recherche est importante car elle s'attaque aux limitations existantes en matière d'équité et de performance, garantissant que l'algorithme peut atteindre des résultats optimaux sans compromettre l'équité. En introduisant un schéma d'arrondi sans perte, l'étude promet d'améliorer l'efficacité de la distribution des ressources, ce qui en fait une avancée cruciale dans le domaine.

A new study on online multi-class selection with group fairness guarantees has been released, presenting innovative solutions to improve resource allocation among sequentially arriving agents. This research is significant as it tackles existing limitations in fairness and performance, ensuring that the algorithm can achieve optimal results without compromising on fairness. By introducing a lossless rounding scheme, the study promises to enhance the effectiveness of resource distribution, making it a crucial advancement in the field.

Online Multi-Class Selection with Group Fairness Guarantee

arXiv:2411.00365v2 Announce Type: replace 
Abstract: In the paradigm of decentralized learning, a group of agents collaborate to learn a global model using a distributed dataset without a central server; nevertheless, it is severely challenged by the heterogeneity of the data distribution across the agents. For example, the data may be distributed non-independently and identically, and even be noised or poisoned. To address these data challenges, we propose ROSS, a novel robust decentralized stochastic learning algorithm based on Shapley values, in this paper. Specifically, in each round, each agent aggregates the cross-gradient information from its neighbors, i.e., the derivatives of its local model with respect to the datasets of its neighbors, to update its local model in a momentum like manner, while we innovate in weighting the derivatives according to their contributions measured by Shapley values. We perform solid theoretical analysis to reveal the linear convergence speedup of our ROSS algorithm. We also verify the efficacy of our algorithm through extensive experiments on public datasets. Our results demonstrate that, in face of the above variety of data challenges, our ROSS algorithm has significant advantages over existing state-of-the-art proposals in terms of both convergence and prediction accuracy.

تم اقتراح خوارزمية جديدة للتعلم اللامركزي تُدعى ROSS، والتي تستخدم قيم شابلي لتعزيز قوة التعلم العشوائي بين الوكلاء. تتناول هذه الطريقة التحديات التي تطرحها توزيعات البيانات غير المتجانسة، مما يسمح للوكلاء بتعلم نموذج عالمي بشكل تعاوني دون الحاجة إلى خادم مركزي. يقوم كل وكيل بتحديث نموذجه من خلال تجميع معلومات التدرج المتقاطع من الوكلاء المجاورين، مع وزنها وفقًا لمساهماتهم.

Se ha propuesto un nuevo algoritmo de aprendizaje descentralizado llamado ROSS, que utiliza valores de Shapley para mejorar la robustez del aprendizaje estocástico entre agentes. Este enfoque aborda los desafíos planteados por las distribuciones de datos heterogéneas, permitiendo que los agentes aprendan de manera colaborativa un modelo global sin un servidor central. Cada agente actualiza su modelo agregando información de gradiente cruzado de los agentes vecinos, ponderada por sus contribuciones.

Un nouvel algorithme d'apprentissage décentralisé nommé ROSS a été proposé, utilisant les valeurs de Shapley pour améliorer la robustesse de l'apprentissage stochastique parmi les agents. Cette approche répond aux défis posés par les distributions de données hétérogènes, permettant aux agents d'apprendre de manière collaborative un modèle global sans serveur central. Chaque agent met à jour son modèle en agrégeant des informations de gradient croisé provenant des agents voisins, pondérées par leurs contributions.

A new decentralized learning algorithm named ROSS has been proposed, which utilizes Shapley values to enhance the robustness of stochastic learning among agents. This approach addresses challenges posed by heterogeneous data distributions, allowing agents to collaboratively learn a global model without a central server. Each agent updates its model by aggregating cross-gradient information from neighboring agents, weighted by their contributions.

ROSS: RObust decentralized Stochastic learning based on Shapley values

One More Thing in AI – Your Shortcut to AI Mastery

Online Multi-Class Selection with Group Fairness Guarantee

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

Https

Solvice

Teilord

Superset

Ready to build your own newsroom?