Graph classification Gaussian processes via spectral features
Graph classification aims to categorise graphs based on their structure and node attributes. In this work, we propose to tackle this task using tools from graph signal processing by deriving spectral features, which we then use to design two variants of Gaussian process models for graph classificati...
| Glavni autori: | , , , |
|---|---|
| Format: | Conference item |
| Jezik: | English |
| Izdano: |
Proceedings of Machine Learning Research
2023
|