Knowledge-Enhanced Contextual Auction Design Based on Deep Neural Networks

The optimal auction represents a fundamental challenge in auction design, primarily focused on maximizing the seller's revenue. Recently, context-aware auction design has gained traction as it enhances the model's understanding of the auction environment by incorporating contextual informa...

Full description

Saved in:
Bibliographic Details
Published in2024 IEEE International Conference on Cognitive Computing and Complex Data (ICCD) pp. 181 - 188
Main Authors Liang, Mingxuan, Guo, Zhibo, Zhu, Junwu, Zhang, Yuanyuan, Li, Xueqing
Format Conference Proceeding
LanguageEnglish
Published IEEE 28.09.2024
Subjects
Auction Design
Computational modeling
Context modeling
Correlation
Data models
Deep Learning
Encyclopedias
Internet
Knowledge based systems
Knowledge Graph
Knowledge graphs
Online services
Optimal Auction
Real-time systems
Online AccessGet full text

Cover

More Information
Summary:The optimal auction represents a fundamental challenge in auction design, primarily focused on maximizing the seller's revenue. Recently, context-aware auction design has gained traction as it enhances the model's understanding of the auction environment by incorporating contextual information about buyers and items. However, limited contextual information can hinder the model's ability to capture potential correlations. Therefore, we propose a Knowledge-Enhanced Contextual Auction Design Model (KECA) based on neural networks. KECA aims to improve the comprehensive understanding of the auction environment by integrating external knowledge. Specifically, we first construct a structured knowledge graph of triples using Wikipedia. This knowledge graph is utilized to enhance the contextual feature representation of buyers and items, thereby providing a more comprehensive description of the information in the auction environment. Additionally, we employ the K-means clustering algorithm to enhance feature fusion between auction information and the knowledge graph within the locally sensitive hashing self-attention mechanism, thereby improving the model's feature representation capabilities. Finally, extensive experimental results indicate that KECA outperforms current mainstream auction models under various settings, verifying the effectiveness of this approach.
DOI:10.1109/ICCD62811.2024.10843416