paper-with-me

Papers

A Unified Framework for Convolution-based Graph Neural Networks

2021-01-01 · Xuran Pan, Shiji Song, Gao Huang

Graph Convolutional Networks (GCNs) have attracted a lot of research interest in the machine learning community in recent years. Although many variants have been proposed, we still lack a systematic view of different GCN models and deep understanding of the relations among them. In this paper, we take a step forward to establish a unified framework for convolution-based graph neural networks, by formulating the basic graph convolution operation as an optimization problem in the graph Fourier space. Under this framework, a variety of popular GCN models, including the vanilla-GCNs, attention-based GCNs and topology-based GCNs, can be interpreted as a same optimization problem but with different carefully designed regularizers. This novel perspective enables a better understanding of the similarities and differences among many widely used GCNs, and may inspire new approaches for designing better models. As a showcase, we also present a novel regularization technique under the proposed framework to tackle the oversmoothing problem in graph convolution. The effectiveness of the newly designed model is validated empirically.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Similar Papers 제목 키워드 기반

Functional Graph Convolutional Networks: A unified multi-task and multi-modal learning framework to facilitate health and social-care insights

2024-03-15 · Tobia Boschi, Francesca Bonin, Rodrigo Ordonez-Hurtado, Cécile Rousseau 외

This paper introduces a novel Functional Graph Convolutional Network (funGCN) framework that combines Functional Data Analysis and Graph Convolutional Networks to address the complexities of multi-task and multi-modal le…

Unifying Graph Embedding Features with Graph Convolutional Networks for Skeleton-based Action Recognition

2020-03-06 · Dong Yang, Monica Mengqi Li, Hong Fu, Jicong Fan 외

Combining skeleton structure with graph convolutional networks has achieved remarkable performance in human action recognition. Since current research focuses on designing basic graph for representing skeleton data, thes…

Action RecognitionGraph EmbeddingSkeleton Based Action RecognitionTemporal Action Localization

CKGConv: General Graph Convolution with Continuous Kernels

2024-04-21 · Liheng Ma, Soumyasundar Pal, Yitian Zhang, Jiaming Zhou 외

The existing definitions of graph convolution, either from spatial or spectral perspectives, are inflexible and not unified. Defining a general convolution operator in the graph domain is challenging due to the lack of c…

Graph ClassificationGraph LearningGraph RegressionNode Classification

Unified Line and Paragraph Detection by Graph Convolutional Networks

2022-03-17 · Shuang Liu, Renshen Wang, Michalis Raptis, Yasuhisa Fujii

We formulate the task of detecting lines and paragraphs in a document into a unified two-level clustering problem. Given a set of text detection boxes that roughly correspond to words, a text line is a cluster of boxes a…

ClusteringText Detection

Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected Graphs

2022-03-31 · Jiying Zhang, Fuyang Li, Xi Xiao, Tingyang Xu 외

As a powerful tool for modeling complex relationships, hypergraphs are gaining popularity from the graph learning community. However, commonly used frameworks in deep hypergraph learning focus on hypergraphs with edge-in…

Graph Learning