Blockchain technology has evolved from its initial use in decentralized payments to encompass smart contracts and applications across multiple domains, propelling the digital transformation of various industries. However, the decentralized and anonymous nature of blockchain presents challenges for anomaly detection (AD), increasing the complexity of security management. The core issue lies in how to efficiently process massive amounts of data and accurately identify anomalous transactions. To address these challenges, this article proposes an innovative method called behavioral AD based on contrastive learning and relational mechanisms (BAD-CLRM), which aims to leverage a large amount of unlabeled data in the blockchain and the relationships between the features of various transaction nodes. We explore the feature distribution of temporal transaction nodes and infer the label attributes of node clusters through contrastive learning, thereby maximizing model learning efficiency and reducing manual labeling costs. Consequently, we leverage the relational mechanism to construct behavioral and structural feature information of nodes during transactions, providing a comprehensive understanding and support for node AD. Experimental results demonstrate that our model exhibits flexibility, superiority, and efficiency in AD tasks, outperforming existing models, especially in handling dynamic transaction data and unlabeled data.
25 October 2025 in Journal of Intelligent Information Systems
Graph Neural Networks (GNNs) have significant advantages in handling non-Euclidean data and have been widely applied across various areas, thus receiving increasing attention in recent years. The framework of GNN models mainly includes the information propagation phase and the aggregation phase, treating nodes and edges as information entities and propagation channels, respectively. However, most existing GNN models face the challenge of disconnection between node and edge feature information, as these models typically treat the learning of edge and node features as independent tasks. To address this limitation, we aim to develop an edge-empowered graph feature preference learning framework that can capture edge embeddings to assist node embeddings. By leveraging the learned multidimensional edge feature matrix, we construct multi-channel filters to more effectively capture accurate node features, thereby obtaining the non-local structural characteristics and fine-grained high-order node features. Specifically, the inclusion of multidimensional edge information enhances the functionality and flexibility of the GNN model, enabling it to handle complex and diverse graph data more effectively. Additionally, integrating relational representation learning into the message passing framework allows graph nodes to receive more useful information, thereby facilitating node representation learning. Finally, experiments on four real-world heterogeneous graphs demonstrate the effectiveness of theproposed model.