paper-with-me

홈 › Papers

Decimated Framelet System on Graphs and Fast G-Framelet Transforms

2020-12-12 · Xuebin Zheng, Bingxin Zhou, Yu Guang Wang, Xiaosheng Zhuang

Graph representation learning has many real-world applications, from super-resolution imaging, 3D computer vision to drug repurposing, protein classification, social networks analysis. An adequate representation of graph data is vital to the learning performance of a statistical or machine learning model for graph-structured data. In this paper, we propose a novel multiscale representation system for graph data, called decimated framelets, which form a localized tight frame on the graph. The decimated framelet system allows storage of the graph data representation on a coarse-grained chain and processes the graph data at multi scales where at each scale, the data is stored at a subgraph. Based on this, we then establish decimated G-framelet transforms for the decomposition and reconstruction of the graph data at multi resolutions via a constructive data-driven filter bank. The graph framelets are built on a chain-based orthonormal basis that supports fast graph Fourier transforms. From this, we give a fast algorithm for the decimated G-framelet transforms, or FGT, that has linear computational complexity O(N) for a graph of size N. The theory of decimated framelets and FGT is verified with numerical examples for random graphs. The effectiveness is demonstrated by real-world applications, including multiresolution analysis for traffic network, and graph neural networks for graph classification tasks.

📄 PDF Abstract BibTeX arXiv:2012.06922

Code (1)

YuGuangWang/FGT 공식 구현 pytorch

Tasks

Graph ClassificationGraph Representation LearningRepresentation LearningSuper-Resolution

Similar Papers 제목 키워드 기반

Generalized Laplacian Regularized Framelet Graph Neural Networks

2022-10-27 · Zhiqi Shao, Andi Han, Dai Shi, Andrey Vasnev 외

This paper introduces a novel Framelet Graph approach based on p-Laplacian GNN. The proposed two models, named p-Laplacian undecimated framelet graph convolution (pL-UFG) and generalized p-Laplacian undecimated framelet …

DenoisingGraph LearningNode Classification

A Magnetic Framelet-Based Convolutional Neural Network for Directed Graphs

2022-10-20 · Lequan Lin, Junbin Gao

Spectral Graph Convolutional Networks (spectral GCNNs), a powerful tool for analyzing and processing graph data, typically apply frequency filtering via Fourier transform to obtain representations with selective informat…

DenoisingLink PredictionNode Classification

Data-Adaptive Graph Framelets with Generalized Vanishing Moments for Graph Signal Processing

2023-09-07 · Ruigang Zheng, Xiaosheng Zhuang

In this paper, we propose a novel and general framework to construct tight framelet systems on graphs with localized supports based on hierarchical partitions. Our construction provides parametrized graph framelet system…

Denoising

Permutation Equivariant Graph Framelets for Heterophilous Graph Learning

2023-06-07 · Jianfei Li, Ruigang Zheng, Han Feng, Ming Li 외

The nature of heterophilous graphs is significantly different from that of homophilous graphs, which causes difficulties in early graph neural network models and suggests aggregations beyond the 1-hop neighborhood. In th…

Graph LearningGraph Neural Network

Framelet Message Passing

2023-02-28 · Xinliang Liu, Bingxin Zhou, Chutian Zhang, Yu Guang Wang

Graph neural networks (GNNs) have achieved champion in wide applications. Neural message passing is a typical key module for feature propagation by aggregating neighboring features. In this work, we propose a new message…

Node Classification