Marked Neural Spatio-Temporal Point Process Involving a Dynamic Graph Neural Network
This work addresses the need for learning on dynamic graph data across various scientific fields, but it is incremental as it builds on existing neural TPPs for dynamic graphs.
The authors tackled the problem of modeling fully dynamic graph streams, where both structure and attributes change, by proposing a Marked Neural Spatio-Temporal Point Process (MNSTPP) that leverages a Dynamic Graph Neural Network to handle attributes and spatial data for event prediction.
Temporal Point Processes (TPPs) have recently become increasingly interesting for learning dynamics in graph data. A reason for this is that learning on dynamic graph data is becoming more relevant, since data from many scientific fields, ranging from mathematics, biology, social sciences, and physics to computer science, is naturally related and inherently dynamic. In addition, TPPs provide a meaningful characterization of event streams and a prediction mechanism for future events. Therefore, (semi-)parameterized Neural TPPs have been introduced whose characterization can be (partially) learned and, thus, enable the representation of more complex phenomena. However, the research on modeling dynamic graphs with TPPs is relatively young, and only a few models for node attribute changes or evolving edges have been proposed yet. To allow for learning on fully dynamic graph streams, i.e., graphs that can change in their structure (addition/deletion of nodes/edge) and in their node/edge attributes, we propose a Marked Neural Spatio-Temporal Point Process (MNSTPP). It leverages a Dynamic Graph Neural Network to learn a Marked TPP that handles attributes and spatial data to model and predict any event in a graph stream.