Goal-oriented Communications based on Recursive Early Exit Neural Networks

TL;DR

This paper introduces a goal-oriented semantic communication framework using recursive early exit neural networks, optimizing computation and offloading strategies via reinforcement learning to balance accuracy, latency, and resource use.

Contribution

It proposes a novel recursive early exit strategy combined with RL-based optimization for adaptive, efficient edge inference in goal-oriented communications.

Findings

Effective trade-off between performance and latency

Adaptive offloading based on confidence levels

Improved resource efficiency in edge inference

Abstract

This paper presents a novel framework for goal-oriented semantic communications leveraging recursive early exit models. The proposed approach is built on two key components. First, we introduce an innovative early exit strategy that dynamically partitions computations, enabling samples to be offloaded to a server based on layer-wise recursive prediction dynamics that detect samples for which the confidence is not increasing fast enough over layers. Second, we develop a Reinforcement Learning-based online optimization framework that jointly determines early exit points, computation splitting, and offloading strategies, while accounting for wireless conditions, inference accuracy, and resource costs. Numerical evaluations in an edge inference scenario demonstrate the method's adaptability and effectiveness in striking an excellent trade-off between performance, latency, and resource efficiency.