Pyramid Graph Neural Network: A Graph Sampling and Filtering Approach for Multi-scale Disentangled Representations
Open Access
- 4 August 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 518-530
Abstract
Spectral methods for graph neural networks (GNNs) have achieved great success. Despite their success, many works have shown that existing approaches are mainly focused on low-frequency information which may not be pertinent to the task at hand. Recent efforts have been made to design new graph filters for wider frequency profiles, but it remains an open problem how to learn multi-scale disentangled node embeddings in the graph Fourier domain. In this paper, we propose a graph (signal) sampling and filtering framework, entitled Pyramid Graph Neural Network (PyGNN), which follows the Downsampling-Filtering-Upsampling-Decoding scheme. To be specific, we develop an ω-bandlimited downsampling approach to split input graph into subgraphs for the reduction of high-frequency components, then perform spectral graph filters on subgraphs to achieve node embeddings with different frequency bands, and propose a Laplacian smoothing-based upsampling approach to extrapolate the node embedding on subgraphs to the full set of vertices on the original graph. In the end, we add frequency-aware gated units to decode node embeddings of different frequencies for downstream tasks. Results on both homophilic and heterophilic graph datasets show its superiority over state-of-the-art methods.Keywords
Funding Information
- Science and Technology Commission of Shanghai Municipality (22511105100)
- China Key Research and Development Program (2020AAA0107600)
- NSFC (62222607)
This publication has 35 references indexed in Scilit:
- Sparse representation on graphs by tight wavelet frames and applicationsApplied and Computational Harmonic Analysis, 2017
- Autoregressive Moving Average Graph FilteringIEEE Transactions on Signal Processing, 2016
- Efficient Sampling Set Selection for Bandlimited Graph Signals Using Graph Spectral ProxiesIEEE Transactions on Signal Processing, 2016
- Vertex-frequency analysis on graphsApplied and Computational Harmonic Analysis, 2016
- A Multiscale Pyramid Transform for Graph SignalsIEEE Transactions on Signal Processing, 2015
- The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domainsIEEE Signal Processing Magazine, 2013
- Wavelets on graphs via spectral graph theoryApplied and Computational Harmonic Analysis, 2011
- Variational Splines and Paley–Wiener Spaces on Combinatorial GraphsConstructive Approximation, 2008
- Spectral Graph Theory1996
- A New Approach to Linear Filtering and Prediction ProblemsJournal of Basic Engineering, 1960