paper-with-me

Papers

MGC: A Complex-Valued Graph Convolutional Network for Directed Graphs

2021-10-14 · Jie Zhang, Bo Hui, Po-Wei Harn, Min-Te Sun, Wei-Shinn Ku

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 information. To address this issue, we introduce the magnetic Laplacian, a discrete Schr\"odinger operator with magnetic field, which preserves edge directionality by encoding it into a complex phase with an electric charge parameter. By adopting a truncated variant of PageRank named Linear- Rank, we design and build a low-pass filter for homogeneous graphs and a high-pass filter for heterogeneous graphs. In this work, we propose a complex-valued graph convolutional network named Magnetic Graph Convolutional network (MGC). With the corresponding complex-valued techniques, we ensure our model will be degenerated into real-valued when the charge parameter is in specific values. We test our model on several graph datasets including directed homogeneous and heterogeneous graphs. The experimental results demonstrate that MGC is fast, powerful, and widely applicable.

📄 PDF Abstract BibTeX arXiv:2110.07570

Code (1)

hazdzz/MGC_v2 공식 구현 pytorch

Tasks

Graph Representation LearningNode ClassificationRepresentation Learning

Methods 이 논문이 사용한 방법론

Test 설명 없음
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…

Similar Papers 제목 키워드 기반

Graph Learning in 4D: a Quaternion-valued Laplacian to Enhance Spectral GCNs

2023-12-28 · Stefano Fiorini, Stefano Coniglio, Michele Ciavotta, Enza Messina

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 …

Graph Learning

A Magnetic Framelet-Based Convolutional Neural Network for Directed Graphs

2022-10-20 · Lequan Lin, Junbin Gao

Spectral Graph Convolutional Networks (spectral GCNNs), a powerful tool for analyzing and processing graph data, typically apply frequency filtering via Fourier transform to obtain representations with selective informat…

DenoisingLink PredictionNode Classification

Koopman-based spectral clustering of directed and time-evolving graphs

2022-04-06 · Stefan Klus, Natasa Djurdjevac Conrad

While spectral clustering algorithms for undirected graphs are well established and have been successfully applied to unsupervised machine learning problems ranging from image segmentation and genome sequencing to signal…

ClusteringImage SegmentationSemantic Segmentation

Skew-Symmetric Adjacency Matrices for Clustering Directed Graphs

2022-03-02 · Koby Hayashi, Sinan G. Aksoy, Haesun Park

Cut-based directed graph (digraph) clustering often focuses on finding dense within-cluster or sparse between-cluster connections, similar to cut-based undirected graph clustering methods. In contrast, for flow-based clu…

ClusteringGraph Clustering

Directional Sheaf Hypergraph Networks: Unifying Learning on Directed and Undirected Hypergraphs

2025-10-06 · Emanuele Mule, Stefano Fiorini, Antonio Purificato, Federico Siciliano 외 arxiv

Hypergraphs provide a natural way to represent higher-order interactions among multiple entities. While undirected hypergraphs have been extensively studied, the case of directed hypergraphs, which can model oriented gro…