NeuE: Automated Neural Network Ensembles for Edge Intelligence
NeuE: Automated Neural Network Ensembles for Edge Intelligence
复制标题
DOI：
10.1109/tetc.2022.3214931
复制
发表时间：
2023-04
影响因子：
5.9
通讯作者：
Yang Bai;Lixing Chen;Jie Xu
中科院分区：
文献类型：
--
作者：
Yang Bai;Lixing Chen;Jie Xu
人工智能（AI）应用已经在移动的行业中确立，并决定着企业价值创造的进展。本文探讨了边缘计算在增强AI应用程序性能方面的潜力。特别地，研究了DNN集成形成（DEF）问题，该问题考虑边缘计算系统的设备异构性、计算资源限制和服务期限，明智地为DNN集成招募成员，以试图优化边缘AI服务的性能。我们设计了一种新的算法，称为神经网络（NeuE）来解决DEF问题。NeuE涉及一个在线学习过程，该过程学习DNN集成的实际性能，并根据已接纳任务的特征自适应地形成DNN集成。它利用上下文多臂强盗的框架，并遵循计算资源限制和服务期限的约束。我们还从理论上证明了NeuE提供了渐近最优性。然而，NeuE由于指数增长的集成决策空间而具有较差的可扩展性。然后，我们提出了一个变种的NeuE，称为NeuE-S，加快NeuE。NeuE-S使用集成决策的相似性来识别代表性的集成决策，并使用减少的决策空间进行学习。我们通过理论分析表明，NeuE-S大大降低了计算复杂度，性能损失可以忽略不计。我们在边缘计算测试平台上实现了我们的方法。结果表明，我们的方法大大提高了边缘AI服务的性能。
Artificial Intelligence (AI) applications have been established in the mobile industry and are decisively determining the progress in entrepreneurial value creation. This article explores the potential of Edge Computing to enhance the performance of AI applications. In particular, a DNN ensemble formation (DEF) problem is studied which judiciously recruits members for DNN ensembles considering the device heterogeneity, computing resource limitation, and service deadline of edge computing systems, in an attempt to optimize the performance of edge AI services. We design a novel algorithm called Neural Ensemble (NeuE) to solve the DEF problem. NeuE involves an online learning process that learns the in-practice performance of DNN ensembles and adaptively forms DNN ensembles according to the features of admitted tasks. It leverages the framework of contextual multi-armed bandit and follows the constraints of computing resource limitation and service deadline. We also show theoretically that NeuE provides asymptotic optimality. However, NeuE suffers from poor scalability due to exponentially-growing ensemble decision space. We then propose a variant of NeuE, called NeuE-S, to expedite NeuE. NeuE-S identifies representative ensemble decisions using similarities of ensemble decisions and carries out learning with a reduced decision space. We show via theoretical analysis that NeuE-S drastically reduces the computation complexity with negligible performance loss. We implement our method on an edge computing testbed. The results show that our method dramatically improves the performance of edge AI services.