Neural Temporal Point Process for Forecasting Higher Order and Directional Interactions

arXiv:2301.12210v2 Announce Type: replace
Abstract: Real-world systems are made of interacting entities that evolve with time. Creating models that can forecast interactions by learning the dynamics of entities is an important problem in numerous fields. Earlier works used dynamic graph models to achieve this. However, real-world interactions are more complex than pairwise, as they involve more than two entities, and many of these higher-order interactions have directional components. Examples of these can be seen in communication networks such as email …

abstract arxiv cs.ai cs.lg cs.si dynamic dynamics fields forecast forecasting graph however interactions process systems temporal type world