Recent Advances in Semantic Communications and Networks

Dear Colleagues,

The convergence of artificial intelligence and communication systems is fundamentally reshaping wireless networks as we advance toward 6G and beyond. Traditional bit-centric communication paradigms governed by Shannon theory can be evolving into semantic-oriented frameworks that prioritize meaning over mere data transmission. This paradigm shift has been enabled and accelerated by remarkable advancements in artificial intelligence technologies, ranging from efficient neural network architectures to large language models (LLMs), which have provided the computational foundation for extracting, understanding, and generating contextual information across multiple modalities. These intelligent systems transform network efficiency paradigms by prioritizing information relevance and utility rather than merely optimizing data quantity.

However, while AI technologies offer tremendous potential for semantic communication systems, implementing these advanced solutions in real-world scenarios presents significant challenges. The resource demands of sophisticated AI models make them impractical for direct deployment in constrained environments like IoT networks, edge devices, or autonomous vehicles. Additionally, centralized AI processing raises concerns regarding latency, privacy, and network efficiency in distributed communication scenarios. This creates an urgent need for research along two complementary directions: exploring low-complexity paradigms for efficient semantic processing that can operate within resource constraints, and developing distributed intelligence approaches that effectively leverage AI capabilities across communication networks while addressing privacy and efficiency concerns.

This Special Issue aims to bridge the gap between the semantic intelligence offered by advanced AI technologies and the practical constraints of real-world communication systems. We seek contributions addressing both theoretical foundations and practical implementations that enable semantic-aware communications in diverse deployment scenarios.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but not limited to) the following:

(1) Low-complexity semantic communication systems:

• Bio-inspired approaches for energy-efficient semantic processing;
• Dynamic neural network architectures for adaptive semantic encoding/decoding;
• Network quantization and model compression techniques for resource-constrained semantic communications;
• Lightweight semantic representation learning for edge devices;
• Energy-efficient semantic coding mechanisms.

(2) AI-driven semantic wireless networks:

• Large language model applications in semantic networks;
• Federated learning for distributed semantic communication systems;
• Transfer learning approaches for semantic knowledge sharing over wireless networks;
• Distributed training methodologies for multiple semantic encoders and decoders;
• Multi-agent semantic communication frameworks.

(3) Application domains:

• Semantic communications for IoT and edge computing;
• Extended reality applications utilizing semantic communications;
• Autonomous systems with semantic awareness;
• Multi-modal semantic processing across various data types (text, speech, video).

(4) Fundamental research areas:

• Novel theoretical frameworks for semantic information representation and transmission;
• Semantic metrics, quality assessment, and performance evaluation methodologies;
• End-to-end semantic communication system design and optimization;
• Privacy-preserving semantic communication protocols.

We look forward to receiving your contributions. 

Dr. Zhilong Zhang
Dr. Xiaoshi Song
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• semantic communication
• artificial intelligence
• large language models
• low-complexity
• distributed intelligence
• federated learning
• brain-like computing