Graph Embedding via Diffusion-Wavelets-Based Node Feature Distribution Characterization
This addresses the sparse methods for whole graph embedding, which is important for applications in graph analysis, but is incremental as it builds on existing spectral techniques.
The paper tackles the problem of whole graph representation learning by proposing an unsupervised method using spectral graph wavelets to capture topological similarities, achieving the best performance on 4 real-world datasets and outperforming the state-of-the-art by a considerable margin.
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.