Semantic-Native Communication: A Simplicial Complex Perspective
Semantic communication enables intelligent agents to extract meaning (or semantics) of information via interaction, to carry out collaborative tasks. In this paper, we study semantic communication from a topological space perspective, in which higher-order data semantics live in a simplicial complex. Specifically, a transmitter first maps its data into a $k$-order simplicial complex and then learns its high-order correlations. The simplicial structure and corresponding features are encoded into semantic embeddings in latent space for transmission. Subsequently, the receiver decodes the structure and infers the missing or distorted data. The transmitter and receiver collaboratively train a simplicial convolutional autoencoder to accomplish the semantic communication task. Experiments are carried out on a real dataset of Semantic Scholar Open Research Corpus, where one part of the semantic embedding is missing or distorted during communication. Numerical results show that the simplicial convolutional autoencoder enabled semantic communication effectively rebuilds the simplicial features and infer the missing data with $95\%$ accuracy, while achieving stable performance under channel noise. In contrast, the conventional autoencoder enabled communication fails to infer any missing data. Moreover, our approach is shown to effectively infer the distorted data without prior simplicial structure knowledge at the receiver, by learning extracted semantic information during communications. Leveraging the topological nature of information, the proposed method is also shown to be more reliable and efficient compared to several baselines, notably at low signal-to-noise (SNR) levels.
Code (0)
등록된 구현이 없습니다.
Tasks
Semantic CommunicationSimilar Papers 제목 키워드 기반
Joint Semantic-Native Communication and Inference via Minimal Simplicial Structures
In this work, we study the problem of semantic communication and inference, in which a student agent (i.e. mobile device) queries a teacher agent (i.e. cloud sever) to generate higher-order data semantics living in a sim…
Semantic CommunicationDist2Cycle: A Simplicial Neural Network for Homology Localization
Simplicial complexes can be viewed as high dimensional generalizations of graphs that explicitly encode multi-way ordered relations between vertices at different resolutions, all at once. This concept is central towards …
Signal processing on simplicial complexes
Higher-order networks have so far been considered primarily in the context of studying the structure of complex systems, i.e., the higher-order or multi-way relations connecting the constituent entities. More recently, a…
DenoisingTime SeriesTime Series AnalysisBScNets: Block Simplicial Complex Neural Networks
Simplicial neural networks (SNN) have recently emerged as the newest direction in graph learning which expands the idea of convolutional architectures from node space to simplicial complexes on graphs. Instead of pre-dom…
Graph LearningLink PredictionSimplicial Models for the Epistemic Logic of Faulty Agents
In recent years, several authors have been investigating simplicial models, a model of epistemic logic based on higher-dimensional structures called simplicial complexes. In the original formulation, simplicial models we…
Distributed Computing