Citation Prediction via Influence Representation Using Temporal Graphs

Predicting the impact of publications has become an important research area, which is useful in various scenarios such as technology investment, research direction selection, and technology policymaking. Citation trajectory prediction is one of the most popular tasks in this area. One major challenge of this task is to quantify the influence of publications with integrated structural and temporal features from evolutionary citation graphs. Recent machine learning approaches are based on the aggregation of metadata features from citation graphs. However, richer information on the handling of temporal and attributes remains to be explored. In this paper, we propose CPIR, a new citation trajectory prediction framework that is able to represent the influence (the momentum of citation) of new or existing publications using the history information of all their attributes. Our framework consists of three modules: difference-preserved graph embedding, fine-grained influence representation, and learning-based trajectory calculation. To test the effectiveness of our framework in more situations, we collect and construct a new temporal graph dataset from the real world, named AIPatent, which stems from global patents in the field of artificial intelligence. Experiments are conducted on both the APS academic dataset and our contributed AIPatent dataset. The results demonstrate the strengths of our approach in the citation trajectory prediction task.