论文标题
协作智能的帕累托最佳位分配
Pareto-Optimal Bit Allocation for Collaborative Intelligence
论文作者
论文摘要
在最近的研究中，合作情报（CI）已成为移动/边缘设备上基于人工智能（AI）的服务部署（AI）服务的有前途的框架。在CI中，AI模型（一个深神经网络）在边缘和云之间分配，并且中间特征从边缘子模型发送到云子模型。在本文中，我们研究了多流CI系统中特征编码的位分配。我们使用凸表面与扭曲率理论中的凸表面相似的凸面表面对速率进行建模。使用这样的模型，我们能够为单任务系统和标量的多任务系统提供封闭形式的位分配解决方案。此外，我们为2个k任务系统提供了完整的帕累托设置的分析表征，以及针对三台2任任务系统的帕累托设置的边界。分析结果对文献的各种DNN模型进行了检查，以证明结果的广泛适用性
In recent studies, collaborative intelligence (CI) has emerged as a promising framework for deployment of Artificial Intelligence (AI)-based services on mobile/edge devices. In CI, the AI model (a deep neural network) is split between the edge and the cloud, and intermediate features are sent from the edge sub-model to the cloud sub-model. In this paper, we study bit allocation for feature coding in multi-stream CI systems. We model task distortion as a function of rate using convex surfaces similar to those found in distortion-rate theory. Using such models, we are able to provide closed-form bit allocation solutions for single-task systems and scalarized multi-task systems. Moreover, we provide analytical characterization of the full Pareto set for 2-stream k-task systems, and bounds on the Pareto set for 3-stream 2-task systems. Analytical results are examined on a variety of DNN models from the literature to demonstrate wide applicability of the results
