Cost aware Inference for IoT Devices

[edit]

Pengkai Zhu, Durmus Alp Emre Acar, Nan Feng, Prateek Jain, Venkatesh Saligrama ;
Proceedings of Machine Learning Research, 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.

Related Material