Cost aware Inference for IoT Devices
Pengkai Zhu, Durmus Alp Emre Acar, Nan Feng, Prateek Jain, Venkatesh Saligrama
Abstract
Networked embedded devices (IoTs) of limited CPU, memory and power resources are revolutionizing data gathering, remote monitoring and planning in many consumer and business applications. Nevertheless, resource limitations place a significant burden on their service life and operation, warranting cost-aware methods that are capable of distributively screening redundancies in device information and transmitting informative data. We propose to train a decentralized gated network that, given an observed instance at test-time, allows for activation of select devices to transmit information to a central node, which then performs inference. We analyze our proposed gradient descent algorithm for Gaussian features and establish convergence guarantees under good initialization. We conduct experiments on a number of real-world datasets arising in IoT applications and show that our model results in over 1.5X service life with negligible accuracy degradation relative to a performance achievable by a neural network.
BibTeX
@InProceedings{pmlr-v89-zhu19d,
title = {Cost aware Inference for IoT Devices},
author = {Zhu, Pengkai and Acar, Durmus Alp Emre and Feng, Nan and Jain, Prateek and Saligrama, Venkatesh},
booktitle = {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics},
pages = {2770--2779},
year = {2019},
editor = {Chaudhuri, Kamalika and Sugiyama, Masashi},
volume = {89},
series = {Proceedings of Machine Learning Research},
month = {16--18 Apr},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v89/zhu19d/zhu19d.pdf},
url = {https://proceedings.mlr.press/v89/zhu19d.html},
abstract = {Networked embedded devices (IoTs) of limited CPU, memory and power resources are revolutionizing data gathering, remote monitoring and planning in many consumer and business applications. Nevertheless, resource limitations place a significant burden on their service life and operation, warranting cost-aware methods that are capable of distributively screening redundancies in device information and transmitting informative data. We propose to train a decentralized gated network that, given an observed instance at test-time, allows for activation of select devices to transmit information to a central node, which then performs inference. We analyze our proposed gradient descent algorithm for Gaussian features and establish convergence guarantees under good initialization. We conduct experiments on a number of real-world datasets arising in IoT applications and show that our model results in over 1.5X service life with negligible accuracy degradation relative to a performance achievable by a neural network.}
}