Cooperation of Mobile Devices for Fast Inference of Deep Learning Applications
Tóm tắt
Deep learning stimulates many novel mobile applications, but it is still challenging to enable efficient mobile deep learning applications. Traditional approach tackles this challenge by offloading computation tasks to cloud, which has weaknesses of high bandwidth requirements and long transmission latency. In this paper, we propose to enable collaborative inference among mobile devices. Instead of sending deep learning inference tasks to cloud, we let mobile devices collaboratively share the computation workloads. This is based on an important observation that batching inference tasks on GPUs can accelerate the inference processing speed. To achieve efficient collaboration, we design an algorithm based on partial swarm optimization (PSO) that is a versatile population-based stochastic optimization technique. We also design a distributed algorithm to address the challenge that is difficult to collect global network information and run the centralized algorithm. Moreover, extensive simulations are conducted to evaluate the performance of the designed algorithm. The simulation results show that the collaborative inference scheme can effectively reduce inference time of mobile deep learning applications.
Tài liệu tham khảo
Najafabadi MM, et al (2015) Deep learning applications and challenges in big data analytics. J Big Data 2.1:1
Mao Y, et al (2017) A survey on mobile edge computing: the communication perspective. IEEE Commun Surv Tutor 19.4:2322– 2358
Mach P, Becvar Z (2017) Mobile edge computing: a survey on architecture and computation offloading. arXiv:1702.05309
Wu C, et al (2018) Toward high mobile GPU performance through collaborative workload offloading. IEEE Trans Parallel Distrib Syst 29.2:435–449
Poli R, Kennedy J, Blackwell T (2007) Particle swarm optimization. Swarm Intell 1.1:33–57
Chetlur S, et al (2014) cudnn: efficient primitives for deep learning. arXiv:1410.0759
Canziani A, Paszke A, Culurciello E (2016) An analysis of deep neural network models for practical applications. arXiv:1605.07678
Han S, Mao H, Dally WJ (2015) Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv:1510.00149
Tang Z, et al (2015) Energy-efficient transmission scheduling in mobile phones using machine learning and participatory sensing. IEEE Trans Veh Technol 64.7:3167–3176
Chatzimilioudis G, et al (2012) Crowdsourcing with smartphones. IEEE Internet Comput 16.5:36–44
Heyi MH, Rossi C (2016) On the evaluation of cloud web services for crowdsourcing mobile applications. In: 2016 2nd International conference on cloud computing technologies and applications (CloudTech). IEEE
Yao D, et al (2015) Using crowdsourcing to provide QoS for mobile cloud computing. IEEE Transactions on Cloud Computing
Ke H, Li P, Guo S (2014) Crowdsourcing on mobile cloud: cost minimization of joint data acquisition and processing. In: 2014 IEEE Conference on computer communications workshops (INFOCOM WKSHPS), IEEE
Fan J, Li Q, Cao G (2015) Privacy-aware and trustworthy data aggregation in mobile sensing. In: 2015 IEEE Conference on communications and network security (CNS). IEEE