Lessons Learned and Open Challenges

To identify existing challenges and circumvent potential misleading directions, we briefly introduce the potential scenario of “AI Application on Edge,” and separately discuss open issues related to four enabling technologies that we focus on, i.e., “AI Inference in Edge,” “Edge Computing for AI,” “AI Training at Edge,” and “AI for Optimizing Edge.”

[1]  Jonathan P. How,et al.  Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability , 2017, ICML.

[2]  Yi Wu,et al.  Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments , 2017, NIPS.

[3]  Zhiyuan Liu,et al.  Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.

[4]  Zhenming Liu,et al.  DeepDecision: A Mobile Deep Learning Framework for Edge Video Analytics , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications.

[5]  Takayuki Nishio,et al.  Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge , 2018, ICC 2019 - 2019 IEEE International Conference on Communications (ICC).

[6]  Shimon Whiteson,et al.  Learning to Communicate with Deep Multi-Agent Reinforcement Learning , 2016, NIPS.

[7]  Nenghai Yu,et al.  Asynchronous Stochastic Gradient Descent with Delay Compensation , 2016, ICML.

[8]  Rajesh Krishna Balan,et al.  DeepMon: Mobile GPU-based Deep Learning Framework for Continuous Vision Applications , 2017, MobiSys.

[9]  Nadir Shah,et al.  Orchestration of Microservices for IoT Using Docker and Edge Computing , 2018, IEEE Communications Magazine.

[10]  Jiangchuan Liu,et al.  When deep learning meets edge computing , 2017, 2017 IEEE 25th International Conference on Network Protocols (ICNP).

[11]  Zibin Zheng,et al.  An Overview of Blockchain Technology: Architecture, Consensus, and Future Trends , 2017, 2017 IEEE International Congress on Big Data (BigData Congress).

[12]  H. T. Kung,et al.  BranchyNet: Fast inference via early exiting from deep neural networks , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[13]  Bharat K. Bhargava,et al.  A Blockchain-Enabled Trustless Crowd-Intelligence Ecosystem on Mobile Edge Computing , 2019, IEEE Transactions on Industrial Informatics.

[14]  Stephen A. Jarvis,et al.  SAFA: A Semi-Asynchronous Protocol for Fast Federated Learning With Low Overhead , 2019, IEEE Transactions on Computers.

[15]  Ion Stoica,et al.  Chameleon: scalable adaptation of video analytics , 2018, SIGCOMM.

[16]  Yuan He,et al.  An Open-Source Benchmark Suite for Microservices and Their Hardware-Software Implications for Cloud & Edge Systems , 2019, ASPLOS.

[17]  Nei Kato,et al.  State-of-the-Art Deep Learning: Evolving Machine Intelligence Toward Tomorrow’s Intelligent Network Traffic Control Systems , 2017, IEEE Communications Surveys & Tutorials.

[18]  Soo-Mook Moon,et al.  Blockchain-based edge computing for deep neural network applications , 2018, INTESA@ESWEEK.

[19]  Nei Kato,et al.  The Deep Learning Vision for Heterogeneous Network Traffic Control: Proposal, Challenges, and Future Perspective , 2017, IEEE Wireless Communications.

[20]  Peng Liu,et al.  Low-Cost Video Transcoding at the Wireless Edge , 2016, 2016 IEEE/ACM Symposium on Edge Computing (SEC).

[21]  V. Milutinovic,et al.  A survey of military applications of wireless sensor networks , 2012, 2012 Mediterranean Conference on Embedded Computing (MECO).

[22]  Ju Ren,et al.  Distributed and Efficient Object Detection in Edge Computing: Challenges and Solutions , 2018, IEEE Network.

[23]  Mani B. Srivastava,et al.  Enabling Edge Devices that Learn from Each Other: Cross Modal Training for Activity Recognition , 2018, EdgeSys@MobiSys.

[24]  Indranil Gupta,et al.  Asynchronous Federated Optimization , 2019, ArXiv.

[25]  Blaise Agüera y Arcas,et al.  Communication-Efficient Learning of Deep Networks from Decentralized Data , 2016, AISTATS.

[26]  Wenwu Zhu,et al.  Deep Learning on Graphs: A Survey , 2018, IEEE Transactions on Knowledge and Data Engineering.

[27]  Ming Zhao,et al.  Are Existing Knowledge Transfer Techniques Effective for Deep Learning with Edge Devices? , 2018, 2018 IEEE International Conference on Edge Computing (EDGE).

[28]  Hubert Eichner,et al.  Towards Federated Learning at Scale: System Design , 2019, SysML.