Leveraging Network Dynamics for Improved Link Prediction
This is an incremental improvement for researchers and practitioners in network analysis, focusing on enhancing link prediction accuracy.
The paper tackles link prediction by introducing RPM, a supervised framework that models network dynamics using predicted rates of link modifications, and shows it outperforms methods based on network similarity measures.
The aim of link prediction is to forecast connections that are most likely to occur in the future, based on examples of previously observed links. A key insight is that it is useful to explicitly model network dynamics, how frequently links are created or destroyed when doing link prediction. In this paper, we introduce a new supervised link prediction framework, RPM (Rate Prediction Model). In addition to network similarity measures, RPM uses the predicted rate of link modifications, modeled using time series data; it is implemented in Spark-ML and trained with the original link distribution, rather than a small balanced subset. We compare the use of this network dynamics model to directly creating time series of network similarity measures. Our experiments show that RPM, which leverages predicted rates, outperforms the use of network similarity measures, either individually or within a time series.