Spectral Graph Neural Network

Spectral graph neural networks (SGNNs) leverage the spectral properties of graphs—eigenvalues and eigenvectors of the graph Laplacian—to perform graph-based machine learning tasks. Current research focuses on improving the efficiency and expressiveness of SGNNs, exploring various polynomial filter designs and incorporating attention mechanisms to learn node-specific filters, addressing issues like over-smoothing and over-squashing. These advancements enhance the ability of SGNNs to capture both local and global graph structure, leading to improved performance in diverse applications such as node classification, graph representation learning, and solving partial differential equations on irregular domains.

Papers

October 16, 2023

Shape-aware Graph Spectral Learning
Junjie Xu, Enyan Dai, Dongsheng Luo, Xiang Zhang, Suhang Wang
High Frequency Spectral Graph Neural Network Graph Frequency

October 10, 2023

Enhanced Graph Neural Networks with Ego-Centric Spectral Subgraph Embeddings Augmentation
Anwar Said, Mudassir Shabbir, Tyler Derr, Waseem Abbas, Xenofon Koutsoukos
Graph Neural Network Graph Classification Subgraph Structure Spectral Graph Neural Network Robust Graph Ego Graph

March 24, 2023

LON-GNN: Spectral GNNs with Learnable Orthonormal Basis
Qian Tao, Zhen Wang, Wenyuan Yu, Yaliang Li, Zhewei Wei
Spectral Graph Neural Network Spectral Graph Spectral GNN Polynomial Basis

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 11, 2023

A Survey on Spectral Graph Neural Networks
Deyu Bo, Xiao Wang, Yang Liu, Yuan Fang, Yawen Li, Chuan Shi
Graph Neural Network Timely Survey Graph Representation Learning Graph Signal Processing Spectral Graph Neural Network

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

September 1, 2022

MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian
Yixuan He, Michael Permultter, Gesine Reinert, Mihai Cucuringu
Spectral Graph Neural Network Spectral Graph Spectral GNN Synthetic Network Permanent Magnet Laplacian Canonization

July 9, 2022

Rank-Enhanced Low-Dimensional Convolution Set for Hyperspectral Image Denoising
Jinhui Hou, Zhiyu Zhu, Hui Liu, Junhui Hou
Low Rank Image Denoising Hyperspectral Image Classification Spectral Graph Neural Network Hyperspectral Image Denoising 1D Convolution

June 27, 2022

DeStripe: A Self2Self Spatio-Spectral Graph Neural Network with Unfolded Hessian for Stripe Artifact Removal in Light-sheet Microscopy
Yu Liu, Kurt Weiss, Nassir Navab, Carsten Marr, Jan Huisken, Tingying Peng
Hessian Matrix Spectral Graph Neural Network Light Sheet Fluorescence Microscopy Image Destriping Stripe Noise

May 23, 2022

How Powerful are Spectral Graph Neural Networks
Xiyuan Wang, Muhan Zhang
Graph Neural Network Graph Signal Spectral Graph Neural Network Spectral GNN

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 Invariant Network Cultural Sign Spectral Graph Convolution Laplacian Matrix

February 16, 2022

When Does A Spectral Graph Neural Network Fail in Node Classification?
Zhixian Chen, Tengfei Ma, Yang Wang
Node Classification Graph Learning Task Graph Filter Spectral Graph Neural Network Spectral GNN

January 31, 2022

MGNN: Graph Neural Networks Inspired by Distance Geometry Problem
Guanyu Cui, Zhewei Wei
Graph Neural Network Spatio Temporal Spectral Graph Neural Network Geometry Problem Graph Isomorphism Network

November 23, 2021

ChebLieNet: Invariant Spectral Graph NNs Turned Equivariant by Riemannian Geometry on Lie Groups
Hugo Aguettaz, Erik J. Bekkers, Michaël Defferrard
Geometric Deep Learning Lie Group Equivariant Map Riemannian Geometry Spectral Graph Neural Network Group Equivariance