Task-Oriented Low-Label Semantic Communication With Self-Supervised Learning

TL;DR

This paper introduces a self-supervised learning framework for task-oriented semantic communication that improves inference performance with limited labeled data, leveraging unlabeled samples and contrastive learning to outperform existing methods.

Contribution

It develops a novel self-supervised semantic communication framework (SLSCom) that enhances task inference with minimal labeled data by using contrastive learning and information bottleneck optimization.

Findings

SLSCom outperforms traditional digital coding and existing DL-based methods.

The framework maintains high inference accuracy even with few labeled samples.

Performance is robust across different SNR levels and unlabeled data relevance.

Abstract

Task-oriented semantic communication enhances transmission efficiency by conveying semantic information rather than exact messages. Deep learning (DL)-based semantic communication can effectively cultivate the essential semantic knowledge for semantic extraction, transmission, and interpretation by leveraging massive labeled samples for downstream task training. In this paper, we propose a self-supervised learning-based semantic communication framework (SLSCom) to enhance task inference performance, particularly in scenarios with limited access to labeled samples. Specifically, we develop a task-relevant semantic encoder using unlabeled samples, which can be collected by devices in real-world edge networks. To facilitate task-relevant semantic extraction, we introduce self-supervision for learning contrastive features and formulate the information bottleneck (IB) problem to balance the tradeoff between the informativeness of the extracted features and task inference performance. Given the computational challenges of the IB problem, we devise a practical and effective solution by employing self-supervised classification and reconstruction pretext tasks. We further propose efficient joint training methods to enhance end-to-end inference accuracy over wireless channels, even with few labeled samples. We evaluate the proposed framework on image classification tasks over multipath wireless channels. Extensive simulation results demonstrate that SLSCom significantly outperforms conventional digital coding methods and existing DL-based approaches across varying labeled data set sizes and SNR conditions, even when the unlabeled samples are irrelevant to the downstream tasks.