Advertisement

Asynchronous Federated Learning for Geospatial Applications

  • Michael R. SpragueEmail author
  • Amir Jalalirad
  • Marco Scavuzzo
  • Catalin Capota
  • Moritz Neun
  • Lyman Do
  • Michael Kopp
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 967)

Abstract

Federated learning is an emerging collaborative machine-learning paradigm for training models directly on edge devices. The data remains on the edge device and this method is robust under real-world edge data distributions. We present a new asynchronous federated-learning algorithm (‘asynchronous federated learning’) and study its convergence rate when distributed across many edge devices, with hard data constraints, relative to training the same model on a single device. We compare asynchronous federated learning to an existing synchronous method. We evaluate its robustness in real-world situations; for example, devices joining part-way through training or devices with heterogeneous compute resources. We then apply asynchronous federated learning to a challenging geospatial application, namely image-based geolocation using a state-of-the-art convolutional neural network. Our results lay the groundwork for deploying large-scale federated learning as a tool to automatically learn, and continually update, a machine-learned model that encodes location.

Keywords

Federated learning Asynchronous communication Heterogeneous computation Image-based geolocation 

References

  1. 1.
    Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely Connected Convolutional Networks, August 2016. https://arxiv.org/abs/1608.06993
  2. 2.
    Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \(<\)0.5MB model size. arXiv:1602.07360 [cs], February 2016
  3. 3.
    Jiang, Z., Balu, A., Hegde, C., Sarkar, S.: Collaborative Deep Learning in Fixed Topology Networks. arXiv:1706.07880 [cs, stat], June 2017
  4. 4.
    Kendall, A., Grimes, M., Cipolla, R.: PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization. arXiv:1505.07427 [cs], May 2015
  5. 5.
    Keuper, J., Pfreundt, F.J.: Asynchronous Parallel Stochastic Gradient Descent - A Numeric Core for Scalable Distributed Machine Learning Algorithms. arXiv:1505.04956 [cs], May 2015
  6. 6.
    Konečný, J., McMahan, H.B., Ramage, D., Richtárik, P.: Federated Optimization: Distributed Machine Learning for On-Device Intelligence. arXiv:1610.02527 [cs], October 2016
  7. 7.
    McMahan, H.B., Moore, E., Ramage, D., Hampson, S., Arcas, B.A.Y.: Communication-Efficient Learning of Deep Networks from Decentralized Data. arXiv:1602.05629 [cs], February 2016

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.HERE TechnologiesAmsterdamThe Netherlands

Personalised recommendations