paper-with-me

홈 › Papers

A Robust Alternative for Graph Convolutional Neural Networks via Graph Neighborhood Filters

2021-10-02 · Victor M. Tenorio, Samuel Rey, Fernando Gama, Santiago Segarra, Antonio G. Marques

Graph convolutional neural networks (GCNNs) are popular deep learning architectures that, upon replacing regular convolutions with graph filters (GFs), generalize CNNs to irregular domains. However, classical GFs are prone to numerical errors since they consist of high-order polynomials. This problem is aggravated when several filters are applied in cascade, limiting the practical depth of GCNNs. To tackle this issue, we present the neighborhood graph filters (NGFs), a family of GFs that replaces the powers of the graph shift operator with $k$-hop neighborhood adjacency matrices. NGFs help to alleviate the numerical issues of traditional GFs, allow for the design of deeper GCNNs, and enhance the robustness to errors in the topology of the graph. To illustrate the advantage over traditional GFs in practical applications, we use NGFs in the design of deep neighborhood GCNNs to solve graph signal denoising and node classification problems over both synthetic and real-world data.

📄 PDF Abstract BibTeX arXiv:2110.00844

Code (1)

vmtenorio/neighborhoodgf 공식 구현 pytorch

Tasks

DenoisingNode Classification

Similar Papers 제목 키워드 기반

On Local Distributions in Graph Signal Processing

2022-02-22 · T. Mitchell Roddenberry, Fernando Gama, Richard G. Baraniuk, Santiago Segarra

Graph filtering is the cornerstone operation in graph signal processing (GSP). Thus, understanding it is key in developing potent GSP methods. Graph filters are local and distributed linear operations, whose output depen…

Kernel Graph Convolutional Neural Networks

2017-10-29 · Giannis Nikolentzos, Polykarpos Meladianos, Antoine Jean-Pierre Tixier, Konstantinos Skianis 외

Graph kernels have been successfully applied to many graph classification problems. Typically, a kernel is first designed, and then an SVM classifier is trained based on the features defined implicitly by this kernel. Th…

General ClassificationGraph Classification

Action Recognition with Kernel-based Graph Convolutional Networks

2020-12-28 · Hichem Sahbi

Learning graph convolutional networks (GCNs) is an emerging field which aims at generalizing deep learning to arbitrary non-regular domains. Most of the existing GCNs follow a neighborhood aggregation scheme, where the r…

Action RecognitionSkeleton Based Action Recognition

Kernel Graph Convolutional Neural Nets

2018-01-01 · ICLR 2018 1 · Giannis Nikolentzos, Polykarpos Meladianos, Antoine J-P Tixier, Konstantinos Skianis 외

Graph kernels have been successfully applied to many graph classification problems. Typically, a kernel is first designed, and then an SVM classifier is trained based on the features defined implicitly by this kernel. Th…

Graph Classification

On semi shift invariant graph filters

2022-09-28 · Feng Ji, See Hian Lee, Wee Peng Tay

In graph signal processing, one of the most important subjects is the study of filters, i.e., linear transformations that capture relations between graph signals. One of the most important families of filters is the spac…