English
Related papers

Related papers: Haar-Laplacian for directed graphs

200 papers

Graph Neural Networks (GNNs) play a pivotal role in graph-based tasks for their proficiency in representation learning. Among the various GNN methods, spectral GNNs employing polynomial filters have shown promising performance on tasks…

Machine Learning · Computer Science 2025-01-09 Haipeng Ding , Zhewei Wei , Yuhang Ye

It is shown that an undirected graph $G$ is cospectral with the Hermitian adjacency matrix of a mixed graph $D$ obtained from a subgraph $H$ of $G$ by orienting some of its edges if and only if $H=G$ and $D$ is obtained from $G$ by a…

Combinatorics · Mathematics 2015-05-14 Bojan Mohar

Recent advancements in Graph Neural Networks have led to state-of-the-art performance on graph representation learning. However, the majority of existing works process directed graphs by symmetrization, which causes loss of directional…

Machine Learning · Computer Science 2022-02-04 Jie Zhang , Bo Hui , Po-Wei Harn , Min-Te Sun , Wei-Shinn Ku

Complex real-world phenomena across a wide range of scales, from aviation and internet traffic to signal propagation in electronic and gene regulatory circuits, can be efficiently described through dynamic network models. In many such…

Physics and Society · Physics 2018-12-11 Aden Forrow , Francis G. Woodhouse , Jörn Dunkel

We consider spectral methods that uncover hidden structures in directed networks. We establish and exploit connections between node reordering via (a) minimizing an objective function and (b) maximizing the likelihood of a random graph…

Social and Information Networks · Computer Science 2021-10-12 Xue Gong , Desmond John Higham , Konstantinos Zygalakis

We propose a supervised learning approach for predicting an underlying graph from a set of graph signals. Our approach is based on linear regression. In the linear regression model, we predict edge-weights of a graph as the output, given a…

Information Theory · Computer Science 2018-11-06 Arun Venkitaraman , Hermina Petric Maretic , Saikat Chatterjee , Pascal Frossard

Segmentation is an essential operation of image processing. The convolution operation suffers from a limited receptive field, while global modelling is fundamental to segmentation tasks. In this paper, we apply graph convolution into the…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Yanda Meng , Hongrun Zhang , Dongxu Gao , Yitian Zhao , Xiaoyun Yang , Xuesheng Qian , Xiaowei Huang , Yalin Zheng

Hypergraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph-structured data. However, most existing convolution filters are localized and determined by the…

Machine Learning · Computer Science 2022-04-15 Jiying Zhang , Yuzhao Chen , Xi Xiao , Runiu Lu , Shu-Tao Xia

Analysis of signals defined on complex topologies modeled by graphs is a topic of increasing interest. Signal decomposition plays a crucial role in the representation and processing of such information, in particular, to process graph…

Signal Processing · Electrical Eng. & Systems 2025-02-18 Harry H. Behjat , Carl-Fredrik Westin , Rik Ossenkoppele , Dimitri Van De Ville

Hypergraphs provide a robust framework for modeling complex systems with higher-order interactions. However, analyzing them in dynamic settings presents significant computational challenges. To address this, we introduce a novel method that…

Social and Information Networks · Computer Science 2024-10-15 Hiroki Matsumoto , Takahiro Yoshida , Ryoma Kondo , Ryohei Hisano

In this paper we investigated the possibility to use the magnetic Laplacian to characterize directed graphs (a.k.a. networks). Many interesting results are obtained, including the finding that community structure is related to rotational…

Social and Information Networks · Computer Science 2020-08-04 Bruno Messias F. de Resende , Luciano da F. Costa

This paper introduces a graph Laplacian regularization in the hyperspectral unmixing formulation. The proposed regularization relies upon the construction of a graph representation of the hyperspectral image. Each node in the graph…

Computer Vision and Pattern Recognition · Computer Science 2014-10-15 Rita Ammanouil , André Ferrari , Cédric Richard

In this paper, we develop a new aligned vertex convolutional network model to learn multi-scale local-level vertex features for graph classification. Our idea is to transform the graphs of arbitrary sizes into fixed-sized aligned vertex…

Machine Learning · Computer Science 2019-02-27 Lu Bai , Lixin Cui , Shu Wu , Yuhang Jiao , Edwin R. Hancock

Graph representation matrices are essential tools in graph data analysis. Recently, Hermitian adjacency matrices have been proposed to investigate directed graph structures. Previous studies have demonstrated that these matrices can extract…

Combinatorics · Mathematics 2025-07-21 Keishi Sando , Hideitsu Hino

Graph Neural Networks (GNNs) are the subject of intense focus by the machine learning community for problems involving relational reasoning. GNNs can be broadly divided into spatial and spectral approaches. Spatial approaches use a form of…

Machine Learning · Statistics 2021-01-05 Kimberly Stachenfeld , Jonathan Godwin , Peter Battaglia

We introduce QuaterGCN, a spectral Graph Convolutional Network (GCN) with quaternion-valued weights at whose core lies the Quaternionic Laplacian, a quaternion-valued Laplacian matrix by whose proposal we generalize two widely-used…

Machine Learning · Computer Science 2024-01-01 Stefano Fiorini , Stefano Coniglio , Michele Ciavotta , Enza Messina

Learning a suitable graph is an important precursor to many graph signal processing (GSP) pipelines, such as graph spectral signal compression and denoising. Previous graph learning algorithms either i) make some assumptions on connectivity…

Signal Processing · Electrical Eng. & Systems 2021-02-19 Saghar Bagheri , Gene Cheung , Antonio Ortega , Fen Wang

This paper introduces a novel graph signal processing framework for building graph-based models from classes of filtered signals. In our framework, graph-based modeling is formulated as a graph system identification problem, where the goal…

Machine Learning · Computer Science 2018-03-08 Hilmi E. Egilmez , Eduardo Pavez , Antonio Ortega

In this paper we propose a new wavelet transform applicable to functions defined on graphs, high dimensional data and networks. The proposed method generalizes the Haar-like transform proposed in [1], and it is defined via a hierarchical…

Computer Vision and Pattern Recognition · Computer Science 2015-05-20 Idan Ram , Michael Elad , Israel Cohen

An orthogonal Haar scattering transform is a deep network, computed with a hierarchy of additions, subtractions and absolute values, over pairs of coefficients. It provides a simple mathematical model for unsupervised deep network learning.…

Machine Learning · Computer Science 2015-10-01 Xiuyuan Cheng , Xu Chen , Stephane Mallat