Spectral Graph Convolution

Spectral graph convolution is a technique in graph neural networks that leverages the spectral properties of graphs to perform efficient and effective filtering of graph-structured data. Current research focuses on improving the flexibility and expressiveness of spectral graph convolutional networks (GCNs) through novel filter designs, such as wavelet-based approaches and those employing tensor decompositions, as well as exploring alternative polynomial bases beyond the commonly used Chebyshev polynomials. These advancements aim to enhance the ability of GCNs to capture both local and global patterns within graph data, leading to improved performance in various applications, including node classification, graph classification, and spatio-temporal forecasting. The resulting improvements in model accuracy and efficiency have significant implications for diverse fields relying on graph-structured data analysis.

Papers

November 4, 2024

High-Pass Graph Convolutional Network for Enhanced Anomaly Detection: A Novel Approach
Shelei Li, Yong Chai Tan, Tai Vincent
Graph Neural Network Anomaly Detection Novel Approach Graph Convolutional Network Graph Convolutional Neural Network Graph Anomaly Detection Spectral Graph Convolution

September 7, 2024

Generalized Learning of Coefficients in Spectral Graph Convolutional Networks
Mustafa Coşkun, Ananth Grama, Mehmet Koyutürk
Machine Learning Graph Machine Learning Graph Propagation Spectral Graph Convolution Coefficient Prediction Polynomial Filter

May 22, 2024

Advancing Graph Convolutional Networks via General Spectral Wavelets
Nian Liu, Xiaoxin He, Thomas Laurent, Francesco Di Giovanni, Michael M. Bronstein, Xavier Bresson
Spectral Graph Convolution Graph Wavelet

May 6, 2024

Coefficient Decomposition for Spectral Graph Convolution
Feng Huang, Wen Zhang
Deep Convolutional Neural Network Spectral Graph Spectral Graph Convolution Robust Decomposition Graph Signal Filter

April 6, 2024

Spectral GNN via Two-dimensional (2-D) Graph Convolution
Guoming Li, Jian Yang, Shangsong Liang, Dongsheng Luo
2 Dimensional Graph Convolution Spectral Graph Neural Network Spectral GNN Spectral Graph Convolution

March 8, 2024

3D Face Reconstruction Using A Spectral-Based Graph Convolution Encoder
Haoxin Xu, Zezheng Zhao, Yuxin Cao, Chunyu Chen, Hao Ge, Ziyao Liu
3D Face Reconstruction 3D Structure Spectral Graph Convolution Monocular 3D Face Reconstruction Unsupervised Loss Function

January 16, 2024

SpecSTG: A Fast Spectral Diffusion Framework for Probabilistic Spatio-Temporal Traffic Forecasting
Lequan Lin, Dai Shi, Andi Han, Junbin Gao
Traffic Forecasting Traffic Datasets Spatio Temporal Graph Temporal Traffic Spectral Graph Convolution Spectral Diffusion

December 28, 2023

Graph Learning in 4D: a Quaternion-valued Laplacian to Enhance Spectral GCNs
Stefano Fiorini, Stefano Coniglio, Michele Ciavotta, Enza Messina
Graph Learning 4 Dimensional Spectral GNN Spectral Graph Convolution Quaternion Valued Laplacian Matrix Quaternion Matrix

May 10, 2023

Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering
Mingqi Yang, Wenjie Feng, Yanming Shen, Bryan Hooi
Graph Representation Learning GNN Model Graph Learning Task Online Filtering Spectral Graph Convolution Graph Fourier Polynomial Filter

March 2, 2023

Specformer: Spectral Graph Neural Networks Meet Transformers
Deyu Bo, Chuan Shi, Lele Wang, Renjie Liao
Spectral Graph Neural Network Spectral GNN Spectral Graph Convolution

February 10, 2023

PointWavelet: Learning in Spectral Domain for 3D Point Cloud Analysis
Cheng Wen, Jianzhi Long, Baosheng Yu, Dacheng Tao
LeArning Abstract Point Cloud Point Cloud Classification Point Cloud Analysis Wavelet Transform Spectral Domain Spectral Graph Convolution Graph Wavelet

February 9, 2023

SF-SGL: Solver-Free Spectral Graph Learning from Linear Measurements
Ying Zhang, Zhiqiang Zhao, Zhuo Feng
Spectral Graph Neural Network Electronic Design Automation Spectral Graph Convolution Resistor Network

October 20, 2022

A Magnetic Framelet-Based Convolutional Neural Network for Directed Graphs
Lequan Lin, Junbin Gao
Directed Graph Spectral GNN Framelet Transform Spectral Graph Convolution Graph Framelets

October 5, 2022

Graph Classification via Discriminative Edge Feature Learning
Yang Yi, Xuequan Lu, Shang Gao, Antonio Robles-Kelly, Yuejie Zhang
Graph Classification Edge Learning Spectral Graph Convolution

August 23, 2022

A Graph Convolution for Signed Directed Graphs
Taewook Ko, Chong-Kwon Kim
Graph Convolution Directed Graph Adjacency Matrix Spectral Graph Convolution

July 12, 2022

From Spectral Graph Convolutions to Large Scale Graph Convolutional Networks
Matteo Bunino
Graph Convolutional Network Large Graph Semi Supervised Node Classification Spectral Graph Convolution Minibatch Stochastic Quater GCN

June 28, 2022

Learning the Solution Operator of Boundary Value Problems using Graph Neural Networks
Winfried Lötzsch, Simon Ohler, Johannes S. Otterbach
LeArning Abstract Graph Neural Network Numerical Solver Solution Operator Spectral Graph Convolution Value Problem

April 12, 2022

Adaptive Cross-Attention-Driven Spatial-Spectral Graph Convolutional Network for Hyperspectral Image Classification
Jin-Yu Yang, Heng-Chao Li, Wen-Shuai Hu, Lei Pan, Qian Du
Deep Convolutional Neural Network Adaptive Importance Hyperspectral Image Classification Spectral GNN Spectral Attention Spectral Graph Convolution

February 25, 2022

Sign and Basis Invariant Networks for Spectral Graph Representation Learning
Derek Lim, Joshua Robinson, Lingxiao Zhao, Tess Smidt, Suvrit Sra, Haggai Maron, Stefanie Jegelka
Spectral Graph Neural Network Cultural Sign Invariant Network Spectral Graph Convolution Laplacian Matrix

February 4, 2022

Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited
Mingguo He, Zhewei Wei, Ji-Rong Wen
Convolutional Neural Network Graph Drawing Graph Convolution Spectral GNN Spectral Graph Convolution Chebyshev Davidson Algorithm