Graph Embedding via Diffusion-Wavelets-Based Node Feature Distribution Characterization

TL;DR

This paper introduces an unsupervised whole graph embedding method using spectral graph wavelets to capture topological similarities, outperforming existing methods on multiple datasets.

Contribution

It presents a novel spectral graph wavelet-based approach for whole graph embedding, addressing the scarcity of methods at the graph level.

Findings

Achieves state-of-the-art performance on 4 real-world datasets

Outperforms 12 baseline methods significantly

Effective in capturing topological similarities

Abstract

Recent years have seen a rise in the development of representational learning methods for graph data. Most of these methods, however, focus on node-level representation learning at various scales (e.g., microscopic, mesoscopic, and macroscopic node embedding). In comparison, methods for representation learning on whole graphs are currently relatively sparse. In this paper, we propose a novel unsupervised whole graph embedding method. Our method uses spectral graph wavelets to capture topological similarities on each k-hop sub-graph between nodes and uses them to learn embeddings for the whole graph. We evaluate our method against 12 well-known baselines on 4 real-world datasets and show that our method achieves the best performance across all experiments, outperforming the current state-of-the-art by a considerable margin.