arXiv:2510.27647v1 Announce Type: new 
Abstract: Collaborative perception improves task performance by expanding the perception range through information sharing among agents. . Immutable heterogeneity poses a significant challenge in collaborative perception, as participating agents may employ different and fixed perception models. This leads to domain gaps in the intermediate features shared among agents, consequently degrading collaborative performance. Aligning the features of all agents to a common representation can eliminate domain gaps with low training cost. However, in existing methods, the common representation is designated as the representation of a specific agent, making it difficult for agents with significant domain discrepancies from this specific agent to achieve proper alignment. This paper proposes NegoCollab, a heterogeneous collaboration method based on the negotiated common representation. It introduces a negotiator during training to derive the common representation from the local representations of each modality's agent, effectively reducing the inherent domain gap with the various local representations. In NegoCollab, the mutual transformation of features between the local representation space and the common representation space is achieved by a pair of sender and receiver. To better align local representations to the common representation containing multimodal information, we introduce structural alignment loss and pragmatic alignment loss in addition to the distribution alignment loss to supervise the training. This enables the knowledge in the common representation to be fully distilled into the sender.

تقدم NegoCollab نهجًا مبتكرًا لتعزيز الإدراك التعاوني من خلال معالجة التحديات التي تطرحها الوكلاء غير المتجانسين. يركز هذا الأسلوب على محاذاة نماذج الإدراك لوكلاء مختلفين، وهو أمر حاسم لتحسين أداء المهام من خلال تحسين تبادل المعلومات. من خلال سد الفجوات في الميزات المشتركة، تعد NegoCollab بزيادة فعالية الجهود التعاونية بشكل كبير، مما يجعلها تقدمًا ملحوظًا في هذا المجال.

NegoCollab presenta un enfoque innovador para mejorar la percepción colaborativa al abordar los desafíos que plantean los agentes heterogéneos. Este método se centra en alinear los modelos de percepción de diferentes agentes, lo cual es crucial para mejorar el rendimiento de las tareas a través de un mejor intercambio de información. Al cerrar las brechas en las características compartidas, NegoCollab promete aumentar significativamente la efectividad de los esfuerzos colaborativos, convirtiéndose en un avance notable en el campo.

NegoCollab propose une approche innovante pour améliorer la perception collaborative en s'attaquant aux défis posés par des agents hétérogènes. Cette méthode se concentre sur l'alignement des modèles de perception de différents agents, ce qui est crucial pour améliorer la performance des tâches grâce à un meilleur partage d'informations. En comblant les lacunes dans les caractéristiques partagées, NegoCollab promet de renforcer considérablement l'efficacité des efforts collaboratifs, ce qui en fait une avancée remarquable dans le domaine.

NegoCollab introduces an innovative approach to enhance collaborative perception by addressing the challenges posed by heterogeneous agents. This method focuses on aligning the perception models of different agents, which is crucial for improving task performance through better information sharing. By bridging the gaps in shared features, NegoCollab promises to significantly boost the effectiveness of collaborative efforts, making it a noteworthy advancement in the field.

NegoCollab: A Common Representation Negotiation Approach for Heterogeneous Collaborative Perception

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

NegoCollab: A Common Representation Negotiation Approach for Heterogeneous Collaborative Perception

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

SwapAnything.io

Personos

Https

Cometapi-e0d0fd

Ready to build your own newsroom?