Accordion: A Communication-Aware Machine Learning Framework for Next Generation Networks

In this article, we advocate for the design of ad hoc artificial intelligence (AI)/machine learning (ML) models to facilitate their usage in future smart infrastructures based on communication networks. To motivate this, we first review key operations identified by the 3GPP for transferring AI/ML models through 5G networks and the main existing techniques to reduce their communication overheads. We also present a novel communication-aware ML framework, which we refer to as Accordion, that enables an efficient AI/ML model transfer thanks to an overhauled model training and communication protocol. We demonstrate the communication-related benefits of Accordion, analyse key performance trade-offs, and discuss potential research directions within this realm.

Automated summary

In this article, we propose the design of ad hoc AI/ML models for future smart infrastructures based on communication networks. We review key operations for AI/ML model transfer through 5G networks and existing techniques to reduce communication overheads. We introduce Accordion, a novel communication-aware ML framework, which enables efficient AI/ML model transfer through improved training and communication protocols. We demonstrate the benefits, performance trade-offs, and potential research directions within this realm.