arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2509.03353cs.LGcs.AI
收藏

面向车队智能的公平资源分配

Fair Resource Allocation for Fleet Intelligence

Wireless Networking Communications Group (WNCG) Department of Electrical;Computer Engineering The University of Texas at Austin Email

Oguzhan Baser, Kaan Kale, Po-han Li, Sandeep Chinchali

AI总结:

针对传统车队智能资源分配低效不公的问题,研究团队开源Fair-Synergy框架,基于准确率与资源的凹关系实现公平分配,经多模型多数据集验证,性能较基准最高提升25%,并探究了公平性对不同智能体的影响。

摘要:

资源分配对云辅助多智能体智能的性能优化至关重要。传统方法往往忽略智能体各异的计算能力与复杂运行环境,导致资源分配低效且不公。为解决该问题,我们开源了Fair-Synergy(公平协同)算法框架,该框架利用智能体准确率与系统资源间的凹关系,确保车队智能场景下的公平资源分配。我们将传统分配方法拓展至由模型参数、训练数据量和任务复杂度定义的多维机器学习效用空间。我们在MNIST、CIFAR-10、CIFAR-100、BDD、GLUE等数据集上,结合BERT、VGG16、MobileNet、ResNets等先进视觉与语言模型对Fair-Synergy进行评估。实验表明,在多智能体推理场景下Fair-Synergy的表现较标准基准最高提升25%,在多智能体学习场景下最高提升11%。此外,我们还探究了公平程度对最弱势、最优势及平均水平智能体的影响,为实现公平的车队智能提供洞见。

英文摘要:

Resource allocation is crucial for the performance optimization of cloud-assisted multi-agent intelligence. Traditional methods often overlook agents' diverse computational capabilities and complex operating environments, leading to inefficient and unfair resource distribution. To address this, we open-sourced Fair-Synergy, an algorithmic framework that utilizes the concave relationship between the agents' accuracy and the system resources to ensure fair resource allocation across fleet intelligence. We extend traditional allocation approaches to encompass a multidimensional machine learning utility landscape defined by model parameters, training data volume, and task complexity. We evaluate Fair-Synergy with advanced vision and language models such as BERT, VGG16, MobileNet, and ResNets on datasets including MNIST, CIFAR-10, CIFAR-100, BDD, and GLUE. We demonstrate that Fair-Synergy outperforms standard benchmarks by up to 25% in multi-agent inference and 11% in multi-agent learning settings. Also, we explore how the level of fairness affects the least advantaged, most advantaged, and average agents, providing insights for equitable fleet intelligence.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑