English
Related papers

Related papers: Graph Signal Separation with Learnable Spectral Fi…

200 papers

New schemes to recover signals defined in the nodes of a graph are proposed. Our focus is on reconstructing bandlimited graph signals, which are signals that admit a sparse representation in a frequency domain related to the structure of…

Social and Information Networks · Computer Science 2016-08-24 Santiago Segarra , Antonio G. Marques , Geert Leus , Alejandro Ribeiro

A graph convolutional network (GCN) employs a graph filtering kernel tailored for data with irregular structures. However, simply stacking more GCN layers does not improve performance; instead, the output converges to an uninformative…

Machine Learning · Computer Science 2022-11-04 Jin Zeng , Yang Liu , Gene Cheung , Wei Hu

When approaching graph signal processing tasks, graphs are usually assumed to be perfectly known. However, in many practical applications, the observed (inferred) network is prone to perturbations which, if ignored, will hinder performance.…

Signal Processing · Electrical Eng. & Systems 2021-03-11 Samuel Rey , Antonio G. Marques

In network science, the interplay between dynamical processes and the underlying topologies of complex systems has led to a diverse family of models with different interpretations. In graph signal processing, this is manifested in the form…

Social and Information Networks · Computer Science 2017-10-11 Xiaoran Yan , Brian M. Sadler , Robert J. Drost , Paul L. Yu , Kristina Lerman

We introduce a new notion of graph sparsificaiton based on spectral similarity of graph Laplacians: spectral sparsification requires that the Laplacian quadratic form of the sparsifier approximate that of the original. This is equivalent to…

Data Structures and Algorithms · Computer Science 2010-07-22 Daniel A. Spielman , Shang-Hua Teng

Graph classification has recently received a lot of attention from various fields of machine learning e.g. kernel methods, sequential modeling or graph embedding. All these approaches offer promising results with different respective…

Machine Learning · Computer Science 2018-11-13 Nathan de Lara , Edouard Pineau

The abundance of large and heterogeneous systems is rendering contemporary data more pervasive, intricate, and with a non-regular structure. With classical techniques facing troubles to deal with the irregular (non-Euclidean) domain where…

Signal Processing · Electrical Eng. & Systems 2023-12-25 Samuel Rey

Graph partitioning (GP), a.k.a. community detection, is a classic problem that divides nodes of a graph into densely-connected blocks. From a perspective of graph signal processing, we find that graph Laplacian with a negative correction…

Machine Learning · Computer Science 2025-08-28 Meng Qin , Weihua Li , Jinqiang Cui , Sen Pei

Many NLP applications can be framed as a graph-to-sequence learning problem. Previous work proposing neural architectures on this setting obtained promising results compared to grammar-based approaches but still rely on linearisation…

Computation and Language · Computer Science 2018-06-27 Daniel Beck , Gholamreza Haffari , Trevor Cohn

Recommender systems often rely on graph-based filters, such as normalized item-item adjacency matrices and low-pass filters. While effective, the centralized computation of these components raises concerns about privacy, security, and the…

Information Retrieval · Computer Science 2025-01-29 Julien Nicolas , César Sabater , Mohamed Maouche , Sonia Ben Mokhtar , Mark Coates

Graph neural networks (GNN) suffer from severe inefficiency. It is mainly caused by the exponential growth of node dependency with the increase of layers. It extremely limits the application of stochastic optimization algorithms so that the…

Machine Learning · Computer Science 2024-04-23 Hongyuan Zhang , Yanan Zhu , Xuelong Li

Graph neural networks (GNNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GNN model requires a large collection of labeled data and expressive features, which might be inaccessible…

Machine Learning · Computer Science 2019-06-03 Ziniu Hu , Changjun Fan , Ting Chen , Kai-Wei Chang , Yizhou Sun

Graph Learning (GL) is at the core of inference and analysis of connections in data mining and machine learning (ML). By observing a dataset of graph signals, and considering specific assumptions, Graph Signal Processing (GSP) tools can…

Machine Learning · Computer Science 2022-11-08 Aref Einizade , Sepideh Hajipour Sardouie

Spectral graph neural networks (GNNs) learn graph representations via spectral-domain graph convolutions. However, most existing spectral graph filters are scalar-to-scalar functions, i.e., mapping a single eigenvalue to a single filtered…

Machine Learning · Computer Science 2023-03-03 Deyu Bo , Chuan Shi , Lele Wang , Renjie Liao

Network data can be conveniently modeled as a graph signal, where data values are assigned to the nodes of a graph describing the underlying network topology. Successful learning from network data requires methods that effectively exploit…

Signal Processing · Electrical Eng. & Systems 2020-10-22 Samuel Pfrommer , Fernando Gama , Alejandro Ribeiro

We consider network topology identification subject to a signal smoothness prior on the nodal observations. A fast dual-based proximal gradient algorithm is developed to efficiently tackle a strongly convex, smoothness-regularized network…

Machine Learning · Computer Science 2021-10-20 Seyed Saman Saboksayr , Gonzalo Mateos

We build interpretable and lightweight transformer-like neural networks by unrolling iterative optimization algorithms that minimize graph smoothness priors -- the quadratic graph Laplacian regularizer (GLR) and the $\ell_1$-norm graph…

Machine Learning · Computer Science 2024-11-07 Tam Thuc Do , Parham Eftekhar , Seyed Alireza Hosseini , Gene Cheung , Philip Chou

To address the limitations of conventional critically sampled graph filter banks in joint time-vertex signal processing, which require decomposing the joint graph into bipartite subgraphs and thus cannot fully exploit all temporal and…

General Mathematics · Mathematics 2026-03-17 Yu Zhang , Bing-Zhao Li

Machine learning frameworks such as graph neural networks typically rely on a given, fixed graph to exploit relational inductive biases and thus effectively learn from network data. However, when said graphs are (partially) unobserved,…

Machine Learning · Computer Science 2022-05-20 Max Wasserman , Saurabh Sihag , Gonzalo Mateos , Alejandro Ribeiro

The aim of this paper is to propose a novel framework to infer the sheaf Laplacian, including the topology of a graph and the restriction maps, from a set of data observed over the nodes of a graph. The proposed method is based on sheaf…

Signal Processing · Electrical Eng. & Systems 2025-02-03 Leonardo Di Nino , Sergio Barbarossa , Paolo Di Lorenzo
‹ Prev 1 4 5 6 7 8 10 Next ›