Economics of Semantic Communication System: An Auction Approach

  title={Economics of Semantic Communication System: An Auction Approach},
  author={Zi Qin Liew and Hongyang Du and Wei Yang Bryan Lim and Zehui Xiong and Dusit Tao Niyato and Chunyan Miao and Dong In Kim},
—Semantic communication technologies enable wireless edge devices to communicate effectively by transmitting semantic meaning of data. Edge components, such as vehicles in next-generation intelligent transport systems, use well-trained semantic models to encode and decode semantic information extracted from raw and sensor data. However, the limitation in computing resources makes it difficult to support the training process of accurate semantic models on edge devices. As such, edge devices can… 

Knowledge-Aware Semantic Communication System Design and Data Allocation

This paper designs an auto-encoder and auto-decoder that only transmit these keywords and recover the data using the received keywords and the shared knowledge and proposes a greedy algorithm to solve the data allocation problem.

Semantics-Empowered Communication: A Tutorial-cum-Survey

This work proposes to categorize the critical enabling techniques by explicit and implicit reasoning-based methods, and elaborate on how they evolve and contribute to modern content & channel semantics-empowered communications.



Deep Learning Enabled Semantic Communication Systems

This work proposes a deep learning based semantic communication system, named DeepSC, for text transmission, based on the Transformer, which aims at maximizing the system capacity and minimizing the semantic errors by recovering the meaning of sentences, rather than bit- or symbol-errors in traditional communications.

Controlled dropout: A different approach to using dropout on deep neural network

The experimental results show that the proposed controlled dropout is as effective as traditional dropout and implies that controlled dropouts is more efficient when an appropriate dropout rate and number of hidden layers are used.

Optimal auctions through deep learning

This work overviews recent research results that show how tools from deep learning are shaping up to become a powerful tool for the automated design of near-optimal auctions auctions and recovers to a high degree of accuracy essentially all known analytically derived solutions for multi-item settings.

Decentralized Edge Intelligence: A Dynamic Resource Allocation Framework for Hierarchical Federated Learning

A deep learning based auction mechanism is proposed to derive the valuation of each cluster head's services and shows the uniqueness and stability of the proposed evolutionary game, as well as the revenue maximizing properties of the deepLearning based auction.

Performance Optimization for Wireless Semantic Communications over Energy Harvesting Networks

A value decomposition based deep Q network is proposed, which enables the users to jointly find the semantic information transmission and the RB allocation schemes that maximize the sum of all users’ similarities.

Semantic Communication Meets Edge Intelligence

This article introduces an edge-driven training, maintenance, and execution of semantic extraction (SE), and investigates how edge intelligence can be enhanced with SemCom through improving the generalization capabilities of intelligent agents at lower computation overheads and reducing the communication overhead of information exchange.

Goal-Oriented Communication For Real-Time Tracking In Autonomous Systems

This work introduces new goal-oriented sampling and communication policies, which leverage the significance and effectiveness of messages, as a means to generate and transmit only the most “informative” samples for real-time actuation.

Economics of Semantic Communication System in Wireless Powered Internet of Things

This paper proposes a semantic-based energy valuation and takes an economic approach to solve the energy allocation problem as an incentive mechanism design and shows that the revenue of wireless power transmitter is maximized while satisfying Individual Rationality (IR) and Incentive Compatibility (IC).

Task-Oriented Semantic Communications for Multimodal Data

A deep neural network enabled semantic communication system, named MU-DeepSC, is proposed to execute the visual question answering (VQA) task as an example, and the transceiver for MU- DeepSC is designed and optimized jointly to capture the features from the correlated multimodal data for task-oriented transmission.

Semantic Communications With AI Tasks

A semantic communication method with artificial intelligence tasks (SC-AIT), which has much lower bandwidth requirements, and can achieve more than 40% classification accuracy gains compared with the communications at the technical level.