Cost aware Inference for IoT Devices

Pengkai Zhu, Durmus Alp Emre Acar, Nan Feng, Prateek Jain, Venkatesh Saligrama
Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, PMLR 89:2770-2779, 2019.

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.

Cite this Paper


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 = {http://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.} }
Endnote
%0 Conference Paper %T Cost aware Inference for IoT Devices %A Pengkai Zhu %A Durmus Alp Emre Acar %A Nan Feng %A Prateek Jain %A Venkatesh Saligrama %B Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Masashi Sugiyama %F pmlr-v89-zhu19d %I PMLR %P 2770--2779 %U http://proceedings.mlr.press/v89/zhu19d.html %V 89 %X 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.
APA
Zhu, P., Acar, D.A.E., Feng, N., Jain, P. & Saligrama, V.. (2019). Cost aware Inference for IoT Devices. Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 89:2770-2779 Available from http://proceedings.mlr.press/v89/zhu19d.html.

Related Material