Multi-Output Gaussian Processes for Graph-Structured Data

TL;DR

This paper introduces a flexible multi-output Gaussian process regression method tailored for graph-structured data, capturing complex correlations and surpassing existing methods in versatility and expressive power.

Contribution

It presents a novel MOGP-based regression framework for graph data, unifying and extending previous Gaussian process approaches with enhanced flexibility.

Findings

Outperforms existing methods on synthetic data

Effective on real-world graph datasets

Flexible kernel design improves modeling capacity

Abstract

Graph-structured data is a type of data to be obtained associated with a graph structure where vertices and edges describe some kind of data correlation. This paper proposes a regression method on 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 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 is 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.