A Mutually Exciting Latent Space Hawkes Process Model for Continuous-time Networks
This provides a better generative model for dynamic relational data in various domains, though it appears incremental as an extension of Hawkes processes with latent space representations.
The authors tackled the problem of modeling continuous-time networks of relational events by proposing the latent space Hawkes (LSH) model, which uses latent space representations and mutually exciting Hawkes processes, resulting in superior prediction accuracy and more interpretable fits compared to existing models.
Networks and temporal point processes serve as fundamental building blocks for modeling complex dynamic relational data in various domains. We propose the latent space Hawkes (LSH) model, a novel generative model for continuous-time networks of relational events, using a latent space representation for nodes. We model relational events between nodes using mutually exciting Hawkes processes with baseline intensities dependent upon the distances between the nodes in the latent space and sender and receiver specific effects. We demonstrate that our proposed LSH model can replicate many features observed in real temporal networks including reciprocity and transitivity, while also achieving superior prediction accuracy and providing more interpretable fits than existing models.