Revisiting NFT Transactions in Web 3.0 Service Through the Lenses of Higher-Order Network

The rapid expansion of Non-Fungible Tokens (NFTs) ecosystem in Web 3.0 service has produced complex transaction networks that challenge traditional graph analysis methods. To address these limitations, this paper presents a higher-order network framework for modeling and analyzing NFT transaction data. Our approach constructs a multi-layered representation of the NFT ecosystem by integrating temporal hypergraphs and motif-based networks, thereby capturing multiway interactions and temporal dependencies beyond simple pairwise transactions. We target three specific tasks to uncover and leverage latent dependencies in NFT markets. First, we build a temporal hypergraph and motif-based network to encode multientity, multi-token relationships. Next, we develop a Higher-Order Graph Neural Network that incorporates token ownership chains and motif edges to improve node classification, significantly outperforming traditional model in identifying key actor roles. Finally, we propose a link prediction model that integrates shared-token and motif-based features, substantially enhancing accuracy in forecasting new NFT transactions compared to baseline models. Our findings validate that explicitly capturing higher-order dependencies is crucial for robust and interpretable analysis of NFT ecosystems, facilitating better Web 3.0 service.