Skip to main content

Edge or Mobile Papers

This part contains papers of projects of edge or mobile system for ML.

Project

  • deepC is a vendor independent deep learning library, compiler and inference framework designed for small form-factor devices including μControllers, IoT and Edge devices[GitHub]
  • Tengine, developed by OPEN AI LAB, is an AI application development platform for AIoT scenarios launched by OPEN AI LAB, which is dedicated to solving the fragmentation problem of aiot industrial chain and accelerating the landing of AI industrialization. [GitHub]
  • Mobile Computer Vision @ Facebook [GitHub]
  • alibaba/MNN: MNN is a lightweight deep neural network inference engine. It loads models and do inference on devices. [GitHub]
  • XiaoMi/mobile-ai-bench: Benchmarking Neural Network Inference on Mobile Devices [GitHub]
  • XiaoMi/mace-models: Mobile AI Compute Engine Model Zoo [GitHub]
  • Tencent/nccn: ncnn is a high-performance neural network inference computing framework optimized for mobile platforms. [Github]
  • Tencent/TNN: [Github]

Survey

  • Convergence of edge computing and deep learning: A comprehensive survey. [Paper]
    • Wang, X., Han, Y., Leung, V. C., Niyato, D., Yan, X., & Chen, X. (2020).
    • IEEE Communications Surveys & Tutorials, 22(2), 869-904.
  • Deep learning with edge computing: A review. [Paper]
    • Chen, J., & Ran, X.
    • Proceedings of the IEEE, 107(8), 1655-1674.(2019).
  • Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing. [Paper]
    • Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J.
    • arXiv: Distributed, Parallel, and Cluster Computing. (2019).
  • Machine Learning at Facebook: Understanding Inference at the Edge. [Paper]
    • Wu, C., Brooks, D., Chen, K., Chen, D., Choudhury, S., Dukhan, M., ... & Zhang, P.
    • high-performance computer architecture.(2019).

Edge AI Paper

  • Modeling of Deep Neural Network (DNN) Placement and Inference in Edge Computing. [GitHub]
    • Bensalem, M., Dizdarević, J. and Jukan, A., 2020.
    • arXiv preprint arXiv:2001.06901.
  • Latency and Throughput Characterization of Convolutional Neural Networks for Mobile Computer Vision [Paper]
    • Hanhirova, J., Kämäräinen, T., Seppälä, S., Siekkinen, M., Hirvisalo, V. and Ylä-Jääski
    • In Proceedings of the 9th ACM Multimedia Systems Conference (pp. 204-215).
  • Characterizing the Deep Neural Networks Inference Performance of Mobile Applications. [Paper]
    • Ogden, S.S. and Guo, T., 2019.
    • arXiv preprint arXiv:1909.04783.
  • Neurosurgeon: Collaborative intelligence between the cloud and mobile edge. [Paper]
    • Kang, Y., Hauswald, J., Gao, C., Rovinski, A., Mudge, T., Mars, J. and Tang, L., 2017, April.
    • In ACM SIGARCH Computer Architecture News (Vol. 45, No. 1, pp. 615-629). ACM.
  • 26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone [Paper]
    • Wei Niu, Xiaolong Ma, Yanzhi Wang, Bin Ren (ICML2019)
  • NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision [Paper]
    • Fang, Biyi, Xiao Zeng, and Mi Zhang. (MobiCom 2018)
    • Summary: Borrow some ideas from network prune. The pruned model then recovers to trade-off computation resource and accuracy at runtime
  • Lavea: Latency-aware video analytics on edge computing platform [Paper]
    • Yi, Shanhe, et al. (Second ACM/IEEE Symposium on Edge Computing. ACM, 2017.)
  • Scaling Video Analytics on Constrained Edge Nodes [Paper] [GitHub]
    • Canel, C., Kim, T., Zhou, G., Li, C., Lim, H., Andersen, D. G., Kaminsky, M., and Dulloo (SysML 2019)
  • Big/little deep neural network for ultra low power inference.
    • Park, E., Kim, D. Y., Kim, S., Kim, Y. M., Kim, G., Yoon, S., & Yoo, S.
    • international conference on hardware/software codesign and system synthesis.(2015)
  • Collaborative learning between cloud and end devices: an empirical study on location prediction. [Paper]
    • Lu, Y., Shu, Y., Tan, X., Liu, Y., Zhou, M., Chen, Q., & Pei, D.
    • ACM/IEEE Symposium on Edge Computing(2019)
  • Context-Aware Convolutional Neural Network over Distributed System in Collaborative Computing. [Paper]
    • Choi, J., Hakimi, Z., Shin, P. W., Sampson, J., & Narayanan, V. (2019).
    • design automation conference.
  • OpenEI: An Open Framework for Edge Intelligence. [Paper]
    • Zhang, X., Wang, Y., Lu, S., Liu, L., Xu, L., & Shi, W.
    • international conference on distributed computing systems.(2019).
  • Swing: Swarm Computing for Mobile Sensing.[Paper]
    • Fan, S., Salonidis, T., & Lee, B. C.
    • international conference on distributed computing systems(2018).
  • Bottlenet++: An end-to-end approach for feature compression in device-edge co-inference systems. [Paper]
    • Shao, J., & Zhang, J.
    • In 2020 IEEE International Conference on Communications Workshops (ICC Workshops) (pp. 1-6). IEEE.(2020, June).
  • JointDNN: an efficient training and inference engine for intelligent mobile cloud computing services. [Paper]
    • Eshratifar, A. E., Abrishami, M. S., & Pedram, M.
    • IEEE Transactions on Mobile Computing.(2019).
  • TeamNet: A Collaborative Inference Framework on the Edge.
    • Fang, Y., Jin, Z., & Zheng, R.
    • In 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS) (pp. 1487-1496). IEEE. (2019, July).
  • Distributing deep neural networks with containerized partitions at the edge. [Paper]
    • Zhou, L., Wen, H., Teodorescu, R., & Du, D. H. (2019).
    • In 2nd {USENIX} Workshop on Hot Topics in Edge Computing (HotEdge 19).
  • Distributed Machine Learning through Heterogeneous Edge Systems.[Paper]
    • Hu, H., Wang, D., & Wu, C. (2020).
    • In AAAI (pp. 7179-7186).
  • Dynamic adaptive DNN surgery for inference acceleration on the edge. [Paper]
    • Hu, C., Bao, W., Wang, D., & Liu, F. (2019, April).
    • In IEEE INFOCOM 2019-IEEE Conference on Computer Communications (pp. 1423-1431). IEEE.
  • Collaborative execution of deep neural networks on internet of things devices. [Paper]
    • Hadidi, R., Cao, J., Ryoo, M. S., & Kim, H.
    • arXiv preprint arXiv:1901.02537.(2019).
  • DeepThings: Distributed Adaptive Deep Learning Inference on Resource-Constrained IoT Edge Clusters. [Paper]
    • Zhao, Z., Barijough, K. M., & Gerstlauer, A.
    • IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 37(11), 2348-2359.(2018).

Fog AI Paper

  • Fogflow: Easy programming of iot services over cloud and edges for smart cities. [Paper] [GitHub]
    • Cheng, Bin, Gürkan Solmaz, Flavio Cirillo, Ernö Kovacs, Kazuyuki Terasawa, and Atsushi Kitazawa.
    • IEEE Internet of Things Journal 5, no. 2 (2017): 696-707.