Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Graph Signal Processing in Python

Graph Signal Processing in Matlab

Graph signal processing tutorial, presented at the GraphSiP summer school.

A PyTorch-based package built for graph signal processing(especially critical-sampling graph wavelet analysis).

Signal Processing on non-euclidien domain signals

Moving Object Detection for Event-based vision using Graph Spectral Clustering (Python implementation)

Code for AAAI 2023 (Oral) paper "Extracting Low-/High- Frequency Knowledge from Graph Neural Networks and Injecting it into MLPs: An Effective GNN-to-MLP Distillation Framework"

Scattering GCN: overcoming oversmoothness in graph convolutional networks

"Graph Convolutions Enrich the Self-Attention in Transformers!" NeurIPS 2024

Signal recovery and sampling over graphs

Official implementation of "Graph Signal Diffusion Model for Collaborative Filtering" (SIGIR 2024)

This repository contains code for morphology-free analysis of functional fluorescence microscopy. The focal algorithm, Graph-Filtered Time-trace (GraFT) Dictionary Learning, is published in Charles et al. 2022 in the IEEE Transactions of Image Processing.

Code for AAAI21 paper "Scalable and Explainable 1-Bit Matrix Completion via Graph Signal Learning"

Graph construction for images representation

MultiscaleGraphSignalTransforms.jl is a collection of software tools written in the Julia programming language for graph signal processing including HGLET, GHWT, eGHWT, NGWP, Lapped NGWP, and Lapped HGLET. Some of them were originally written in MATLAB by Jeff Irion, but we added more functionalities, e.g., eGHWT, NGWP, etc.

Graph Signal Processing in R

Additional material for "Graph Signal Processing on Complex Networks for Structural Health Monitoring"

VGAResNet: A Unified Visibility Graph Adjacency Matrix-Based Residual Network for Chronic Obstructive Pulmonary Disease Detection Using Lung Sounds

Code for ICLR2023 paper "Graph Signal Sampling for Inductive 1-bit Matrix Completion: a Closed-Form Solution"