公平分配算力资源，提升多智能体系统整体效率与公正性。
Fair Resource Allocation for Fleet Intelligence
- 基于准确率与资源的凹函数关系，实现动态公平分配。
- 多智能体推理性能提升25%，学习阶段提升11%。
- 适合需要公平调度的分布式智能系统研究者。
资源分配对云辅助多智能体智能系统的性能优化至关重要。传统方法常忽视智能体间计算能力差异和复杂运行环境，导致资源分配低效且不公。为此，我们开源了 Fair-Synergy 算法框架，利用智能体准确率与系统资源间的凹函数关系，确保舰队智能中的公平资源分配。该框架扩展了传统分配策略，涵盖由模型参数、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，使用 BERT、VGG16、MobileNet、ResNets 等先进视觉与语言模型评估了 Fair-Synergy。结果表明，在多智能体推理中性能优于基准方法最高达25%，在多智能体学习中提升11%。同时，我们分析了公平性水平对最弱势、最优势及平均智能体的影响，为实现公平的舰队智能提供洞见。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。