Analysis of Core-Periphery Structure Based on Clustering Aggregation in the NFT Transfer Network

With the rise of blockchain technology and the Ethereum platform, non-fungible tokens (NFTs) have emerged as a new class of digital assets. The NFT transfer network exhibits core-periphery structures derived from different partitioning methods, leading to local discrepancies and global diversity. We propose a core-periphery structure characterization method based on Bayesian and stochastic block models (SBMs). This method incorporates prior knowledge to improve the fit of core-periphery structures obtained from various partitioning methods. Additionally, we introduce a locally weighted core-periphery structure aggregation (LWCSA) scheme, which determines local aggregation weights using the minimum description length (MDL) principle. This approach results in a more accurate and representative core-periphery structure. The experimental results indicate that core nodes in the NFT transfer network constitute approximately 2.3-5% of all nodes. Compared to baseline methods, our approach improves the normalized mutual information (NMI) index by 6-10%, demonstrating enhanced structural representation. This study provides a theoretical foundation for further analysis of the NFT market.