Graph Regularized Nonnegative Latent Factor Analysis Model for Temporal Link Prediction in Cryptocurrency Transaction Networks
This work addresses link prediction in cryptocurrency transaction networks, an incremental improvement focusing on incorporating temporal dynamics.
The paper tackled the problem of predicting future transactions in dynamic cryptocurrency networks by proposing a graph-regularized nonnegative latent factor analysis model, which improved accuracy and computational efficiency on a real dataset.
With the development of blockchain technology, the cryptocurrency based on blockchain technology is becoming more and more popular. This gave birth to a huge cryptocurrency transaction network has received widespread attention. Link prediction learning structure of network is helpful to understand the mechanism of network, so it is also widely studied in cryptocurrency network. However, the dynamics of cryptocurrency transaction networks have been neglected in the past researches. We use graph regularized method to link past transaction records with future transactions. Based on this, we propose a single latent factor-dependent, non-negative, multiplicative and graph regularized-incorporated update (SLF-NMGRU) algorithm and further propose graph regularized nonnegative latent factor analysis (GrNLFA) model. Finally, experiments on a real cryptocurrency transaction network show that the proposed method improves both the accuracy and the computational efficiency