Search Our Scientific Publications & Authors

Publications
find publications by category +
Translate page:

Fourier-based and Rational Graph Filters for Spectral Processing.

Authors:
Giuseppe Patane'

IEEE Trans Pattern Anal Mach Intell 2022 May 23;PP. Epub 2022 May 23.

Data are represented as graphs in a wide range of applications, such as Computer Vision (e.g., images) and Graphics (e.g., 3D meshes), network analysis (e.g., social networks), and bio-informatics (e.g., molecules). In this context, our overall goal is the definition of novel Fourier-based and graph filters induced by rational polynomials for graph processing, which generalise polynomial filters and the Fourier transform to non-Euclidean domains. For the efficient evaluation of discrete spectral Fourier-based and wavelet operators, we introduce a spectrum-free approach, which requires the solution of a small set of sparse, symmetric, and well-conditioned linear systems and is oblivious of the evaluation of the Laplacian or kernel spectrum. Approximating arbitrary graph filters with rational polynomials provides a more accurate and numerically stable alternative with respect to polynomials. To achieve these goals, we also study the link between spectral operators, wavelets, and filtered convolution with integral operators induced by spectral kernels.

Download full-text PDF

 Source
http://dx.doi.org/10.1109/TPAMI.2022.3177075DOI Listing
May 2022

Publication Analysis

Top Keywords

graph filters
12
rational polynomials
8
fourier-based wavelet
4
well-conditioned linear
4
symmetric well-conditioned
4
sparse symmetric
4
set sparse
4
small set
4
solution small
4
requires solution
4
approach requires
4
spectrum-free approach
4
introduce spectrum-free
4
operators introduce
4
wavelet operators
4
spectral kernels
4
linear systems
4
discrete spectral
4
fourier-based rational
4
efficient evaluation
4

Keyword Occurance

Similar Publications

Multi-Center and Multi-Channel Pooling GCN for Early AD Diagnosis Based on Dual-Modality Fused Brain Network.

Authors:
Xuegang Song Feng Zhou Alejandro F Frangi Jiuwen Cao Xiaohua Xiao Yi Lei Tianfu Wang Baiying Lei

IEEE Trans Med Imaging 2022 Jun 29;PP. Epub 2022 Jun 29.

For significant memory concern (SMC) and mild cognitive impairment (MCI), their classification performance is limited by confounding features, diverse imaging protocols, and limited sample size. To address the above limitations, we introduce a dual-modality fused brain connectivity network combining resting-state functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI), and propose three mechanisms in the current graph convolutional network (GCN) to improve classifier performance. First, we introduce a DTI-strength penalty term for constructing functional connectivity networks. Read More

View Article and Full-Text PDF
June 2022
Similar Publications

RResolver: efficient short-read repeat resolution within ABySS.

Authors:
Vladimir Nikolić Amirhossein Afshinfard Justin Chu Johnathan Wong Lauren Coombe Ka Ming Nip René L Warren Inanç Birol

BMC Bioinformatics 2022 Jun 21;23(1):246. Epub 2022 Jun 21.

Canada's Michael Smith Genome Sciences Centre at BC Cancer, 570 W 7th Ave, Vancouver, V5Z 4S6, Canada.

Background: De novo genome assembly is essential to modern genomics studies. As it is not biased by a reference, it is also a useful method for studying genomes with high variation, such as cancer genomes. De novo short-read assemblers commonly use de Bruijn graphs, where nodes are sequences of equal length k, also known as k-mers. Read More

View Article and Full-Text PDF
June 2022
Similar Publications

SGFNNs: Signed Graph Filtering-based Neural Networks for Predicting Drug-Drug Interactions.

Authors:
Ming Chen Wei Jiang Yi Pan Jianhua Dai Yunwen Lei Chunyan Ji

J Comput Biol 2022 Jun 20. Epub 2022 Jun 20.

Department of Computer Science, Georgia State University, Atlanta, Georgia, USA.

View Article and Full-Text PDF
June 2022
Similar Publications

Logistics Optimization Strategy Based on Deep Neural Framework.

Authors:
Guangqian Liu Yiming Zhu

Comput Intell Neurosci 2022 6;2022:8367155. Epub 2022 Jun 6.

College of Business Administration and Accountancy, De La Salle University-Dasmariñas, Cavite 4115, Philippines.

We propose a logistics optimization method based on improved graph convolutional networks to address the current problem of low product delivery rate and untimely product delivery during the peak period of e-commerce activities. Our method can learn excellent planning strategies from previous data and can give the best logistics strategy in time during the peak logistics period, which improves the product delivery rate and delivery time of logistics and greatly enhances the return on investment. First, we add a tensor rotation module to the graph convolution layer to better capture the global features of logistics nodes. Read More

View Article and Full-Text PDF
June 2022
Similar Publications

Are Graph Convolutional Networks With Random Weights Feasible?

Authors:
Changqin Huang Ming Li Feilong Cao Hamido Fujita Zhao Li Xindong Wu

IEEE Trans Pattern Anal Mach Intell 2022 Jun 15;PP. Epub 2022 Jun 15.

Graph Convolutional Networks (GCNs), as a prominent example of graph neural networks, are receiving extensive attention for their powerful capability in learning node representations on graphs. There are various extensions, either in sampling and/or node feature aggregation, to further improve GCNs' performance, scalability and applicability in various domains. Still, there is room for further improvements on learning efficiency because performing batch gradient descent using the full dataset for every training iteration, as unavoidable for training (vanilla) GCNs, is not a viable option for large graphs. Read More

View Article and Full-Text PDF
June 2022
Similar Publications
}