TinyML NLP Scheme for Semantic Wireless Sentiment Classification with Privacy Preservation

TL;DR

This paper introduces a TinyML framework called semantic split learning (SL) for privacy-preserving, energy-efficient NLP sentiment analysis on edge devices, outperforming federated learning and centralized methods in power consumption and privacy.

Contribution

The study proposes semantic split learning (SL) as a novel TinyML approach that enhances privacy and reduces energy use in NLP tasks on resource-constrained devices.

Findings

SL reduces computational power and CO2 emissions.

SL increases privacy by fourfold compared to FL.

SL offers a better privacy-efficiency trade-off than FL.

Abstract

Natural Language Processing (NLP) operations, such as semantic sentiment analysis and text synthesis, often raise privacy concerns and demand significant on-device computational resources. Centralized learning (CL) on the edge provides an energy-efficient alternative but requires collecting raw data, compromising user privacy. While federated learning (FL) enhances privacy, it imposes high computational energy demands on resource-constrained devices. This study provides insights into deploying privacy-preserving, energy-efficient NLP models on edge devices. We introduce semantic split learning (SL) as an energy-efficient, privacy-preserving tiny machine learning (TinyML) framework and compare it to FL and CL in the presence of Rayleigh fading and additive noise. Our results show that SL significantly reduces computational power and CO2 emissions while enhancing privacy, as evidenced by a fourfold increase in reconstruction error compared to FL and nearly eighteen times that of CL. In contrast, FL offers a balanced trade-off between privacy and efficiency. Our code is available for replication at our GitHub repository: https://github.com/AhmedRadwan02/TinyEco2AI-NLP.