Gang Zeng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Gang Zeng has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Chao Chen
Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Haoyu Geng
Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Hua Chai
DiDi, Beijing, China
1 shared publication - Junchi Yan
Shanghai Jiao Tong University
1 shared publication - Yixuan He
School of Mathematical and Natural Sciences, Arizona State University, Phoenix, AZ, USA
1 shared publication - Zhaobing Han
DiDi Company, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 518-530
Pyramid Graph Neural Network: A Graph Sampling and Filtering Approach for Multi-scale Disentangled Representations
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.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 518-530
Open AccessPyramid Graph Neural Network: A Graph Sampling and Filtering Approach for Multi-scale Disentangled Representations
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.