Computation-resource-efficient Task-oriented Communications

TL;DR

This paper introduces a novel task-oriented communication method with static and dynamic models, optimizing for resource constraints in devices like mobile phones and UAVs, and demonstrates improved efficiency and accuracy.

Contribution

The paper proposes a new TOC approach with static and dynamic neural network models, enabling efficient computation-resource management and convergence analysis.

Findings

Static model outperforms baselines in dimensions, FLOPs, and accuracy.

Dynamic model improves accuracy and reduces computational demand.

Convergence rate of the proposed methods is $O(1/\sqrt{T})$.

Abstract

The rapid development of deep-learning enabled task-oriented communications (TOC) significantly shifts the paradigm of wireless communications. However, the high computation demands, particularly in resource-constrained systems e.g., mobile phones and UAVs, make TOC challenging for many tasks. To address the problem, we propose a novel TOC method with two models: a static and a dynamic model. In the static model, we apply a neural network (NN) as a task-oriented encoder (TOE) when there is no computation budget constraint. The dynamic model is used when device computation resources are limited, and it uses dynamic NNs with multiple exits as the TOE. The dynamic model sorts input data by complexity with thresholds, allowing the efficient allocation of computation resources. Furthermore, we analyze the convergence of the proposed TOC methods and show that the model converges at rate $O\left(\frac{1}{\sqrt{T}}\right)$ with an epoch of length $T$. Experimental results demonstrate that the static model outperforms baseline models in terms of transmitted dimensions, floating-point operations (FLOPs), and accuracy simultaneously. The dynamic model can further improve accuracy and computational demand, providing an improved solution for resource-constrained systems.