# Random Wavelet Features for Graph Kernel Machines

arXiv: https://arxiv.org/abs/2602.15711 · HTML: https://mlsanity.com/paper/2602.15711/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 14 references that are in the map.
- First posted on arXiv 17 Feb 2026.

## Builds on (most cited first, 5 of 5)

- [Orthogonal Random Features](https://mlsanity.com/paper/1610.09072/) (2016)
- [Taming graph kernels with random features](https://mlsanity.com/paper/2305.00156/) (2023)
- [Random sampling of bandlimited signals on graphs](https://mlsanity.com/paper/1511.05118/) (2015)
- [Compressive Spectral Clustering](https://mlsanity.com/paper/1602.02018/) (2016)
- [General Graph Random Features](https://mlsanity.com/paper/2310.04859/) (2023)

## Abstract (arXiv)

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.