# A new communication paradigm: from bit accuracy to semantic fidelity

arXiv: https://arxiv.org/abs/2101.12649 · HTML: https://mlsanity.com/paper/2101.12649/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jan 2021.

## Built on by (most cited first, 18 of 18)

- [Deep Learning-Enabled Semantic Communication Systems with Task-Unaware Transmitter and Dynamic Data](https://mlsanity.com/paper/2205.00271/) (2022)
- [Performance Optimization for Semantic Communications: An Attention-based Reinforcement Learning Approach](https://mlsanity.com/paper/2208.08239/) (2022)
- [Semantics-Native Communication with Contextual Reasoning](https://mlsanity.com/paper/2108.05681/) (2021)
- [Learning Semantics: An Opportunity for Effective 6G Communications](https://mlsanity.com/paper/2110.08049/) (2021)
- [Reinforcement Learning-powered Semantic Communication via Semantic Similarity](https://mlsanity.com/paper/2108.12121/) (2021)
- [Wireless End-to-End Image Transmission System using Semantic Communications](https://mlsanity.com/paper/2302.13721/) (2023)
- [Cognitive Semantic Communication Systems Driven by Knowledge Graph](https://mlsanity.com/paper/2202.11958/) (2022)
- [Knowledge Base Enabled Semantic Communication: A Generative Perspective](https://mlsanity.com/paper/2311.12443/) (2023)
- [Semantics-Empowered Communication: A Tutorial-cum-Survey](https://mlsanity.com/paper/2212.08487/) (2022)
- [Cognitive Semantic Communication Systems Driven by Knowledge Graph: Principle, Implementation, and Performance Evaluation](https://mlsanity.com/paper/2303.08546/) (2023)
- [Performance Limits of a Deep Learning-Enabled Text Semantic Communication under Interference](https://mlsanity.com/paper/2302.14702/) (2023)
- [Latent Space Alignment for AI-Native MIMO Semantic Communications](https://mlsanity.com/paper/2507.16680/) (2025)
- [Bayesian Inverse Contextual Reasoning for Heterogeneous Semantics-Native Communication](https://mlsanity.com/paper/2306.06403/) (2023)
- [Multi-Task Semantic Communication With Graph Attention-Based Feature Correlation Extraction](https://mlsanity.com/paper/2501.02006/) (2025)
- [Alternate Learning based Sparse Semantic Communications for Visual Transmission](https://mlsanity.com/paper/2309.16681/) (2023)
- [Diffusion-aided Task-oriented Semantic Communications with Model Inversion Attack](https://mlsanity.com/paper/2506.19886/) (2025)
- [SEMASIA: A Large-Scale Dataset of Semantically Structured Latent Representations](https://mlsanity.com/paper/2605.09485/) (2026)
- [EXK-SC: A Semantic Communication Model Based on Information Framework Expansion and Knowledge Collision](https://mlsanity.com/paper/2210.13047/) (2022)

## Abstract (arXiv)

Wireless communication has achieved great success in the past several decades. The challenge is of improving bandwidth with limited spectrum and power consumption, which however has gradually become a bottleneck with evolution going on. The intrinsic problem is that communication is modeled as a message transportation from sender to receiver and pursues for an exact message replication in Shannon's information theory, which certainly leads to large bandwidth and power requirements with data explosion. However, the goal for communication among intelligent agents, entities with intelligence including humans, is to understand the meaning or semantics underlying data, not an accurate recovery of the transmitted messages. The separate first transmission and then understanding is a waste on bandwidth. In this article, we deploy semantics to solve the spectrum and power bottleneck and propose a first understanding and then transmission framework with high semantic fidelity. We first give a brief introduction of semantics covering the definition and properties to show the insights and scope of this paper. Then the proposed communication towards semantic fidelity framework is introduced, which takes the above mentioned properties into account to further improve efficiency. Specially, a semantic transformation is introduced to transform the input into semantic symbols. Different from the conventional transformations in signal processing area, for example discrete cosine transform, the transformation is with data loss, which is also the reason that the proposed framework can achieve large bandwidth saving with high semantic fidelity. Besides, we also discuss semantic noise and performance measurement. To evaluate the effectiveness, a case study of audio transmission is carried out. Finally, we discuss the typical applications and open challenges.