.png){kind=icon}
.png){kind=icon}
Return
Deep Graph Kernel Point Processes over Networks
.png){kind=icon}
PRE
AI
D
R
C
X
DOI：10.1080/10618600.2026.2652934.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Point process models are widely used for continuous time discrete event data, where each data point includes time and additional information called marks-locations, nodes, or event types. We present a new point process model for discrete event data over networks built upon Hawkes' classic influence kernel-based formulation to capture the influence of historical events on future events' occurrence. The key idea is to represent the influence kernel by Graph Neural Networks (GNN) to capture the underlying graph structure while leveraging the strong representation power of GNNs. Compared with prior works focusing on directly modeling the conditional intensity function using neural networks, our kernel presentation harnesses the repeated event influence patterns more effectively by combining statistical and deep models, achieving better model estimation/learning efficiency and superior predictive performance. Our work significantly extends the existing deep spatio-temporal kernel for point process data, which is inapplicable to our setting due to the fundamental difference in the nature of the observation space being Euclidean rather than a graph. We present comprehensive experiments on synthetic and real-world data to show the superior performance of the proposed approach against the state-of-the-art in predicting future events and uncovering the graph structure among data.
Keywords:
Deep kernel
Graph neural networks
Point processes over graphs
Journal
J
IF:
1.8
Papers:
116
Citations:
6.4K
Organization
Cited Papers