A Learning Framework for Bandwidth-Efficient Distributed Inference in Wireless IoT

TL;DR

This paper introduces a deep learning-based framework for compressing sensor data in wireless IoT, optimizing for decision accuracy rather than reconstruction fidelity, and demonstrates superior performance over benchmarks.

Contribution

It presents a novel co-designed compression and quantization framework tailored for sensing goals, without assumptions on data distribution, enhancing distributed inference in wireless IoT.

Findings

Outperforms benchmark models in decision accuracy

Does not rely on assumptions about data distribution

Focuses on maximizing inference accuracy rather than reconstruction fidelity

Abstract

In wireless Internet of things (IoT), the sensors usually have limited bandwidth and power resources. Therefore, in a distributed setup, each sensor should compress and quantize the sensed observations before transmitting them to a fusion center (FC) where a global decision is inferred. Most of the existing compression techniques and entropy quantizers consider only the reconstruction fidelity as a metric, which means they decouple the compression from the sensing goal. In this work, we argue that data compression mechanisms and entropy quantizers should be co-designed with the sensing goal, specifically for machine-consumed data. To this end, we propose a novel deep learning-based framework for compressing and quantizing the observations of correlated sensors. Instead of maximizing the reconstruction fidelity, our objective is to compress the sensor observations in a way that maximizes the accuracy of the inferred decision (i.e., sensing goal) at the FC. Unlike prior work, we do not impose any assumptions about the observations distribution which emphasizes the wide applicability of our framework. We also propose a novel loss function that keeps the model focused on learning complementary features at each sensor. The results show the superior performance of our framework compared to other benchmark models.