.png){kind=icon}
.png){kind=icon}
Return
Multi-Output Gaussian Processes for Graph-Structured Data
.png){kind=icon}
PRE
AI
DOI：10.1109/tsipn.2026.3725577.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Graph-structured data are observations associated with a graph structure in which vertices and edges describe some kind of data correlation. This paper proposes a regression method for graph-structured data, which is based on multi-output Gaussian processes (MOGP), to capture both the correlation between vertices and the correlation between associated data. The proposed formulation is built on the definition of MOGP. This allows it to be applied to a wide range of data configurations and scenarios. Moreover, it has a high expressive capability due to its flexibility in kernel design. It includes existing methods of Gaussian processes for graph-structured data as special cases and makes it possible to remove restrictions on data configurations, model selection, and inference scenarios in the existing methods. The performance of extensions achievable by the proposed formulation is evaluated through computer experiments with synthetic and real data.
Keywords:
Gaussian processes
graph machine learning
graph signal processing
kernel regression
Journal
IF:
4.9
Papers:
727
Citations:
1.9K