Random Wavelet Features for Graph Kernel Machines
Valentin de Bassompierre (PhD candidate, UCLouvain)
| When |
Feb 24, 2026
from 01:00 to 02:00 |
|---|---|
| Where | M7 101 |
| Attendees |
Valentin de Bassompierre |
| Add event to calendar |
vCal
iCal
|
Valentin de Bassompierre
Title: Random Wavelet Features for Graph Kernel Machines
Abstract: Node embeddings map graph vertices into low-dimensional Euclidean spaces while preserving structural information. They are central to tasks such as node classification, link prediction, and signal reconstruction. A key goal is to design node embeddings whose dot products capture meaningful notions of node similarity induced by the graph. Graph kernels offer a principled way to define such similarities, but their direct computation is often prohibitive for large networks. Inspired by random feature methods for kernel approximation in Euclidean spaces, we introduce randomized spectral node embeddings whose dot products estimate a low-rank approximation of any specific graph kernel. We provide theoretical and empirical results showing that our embeddings achieve more accurate kernel approximations than existing methods, particularly for spectrally localized kernels. These results demonstrate the effectiveness of randomized spectral constructions for scalable and principled graph representation learning.
Cette présentation est associée à https://arxiv.org/abs/2602.15711
Cette présentation est associée à https://arxiv.org/abs/2602.15711
Website: https://forge.uclouvain.be/vdebassompie/random-wavelet-features-gkm
In Room M7 101, 1st floor, Monod campus, ENSL.