Multi Graph Neural Network

Multi-graph neural networks (MGNNs) extend the capabilities of standard graph neural networks by leveraging information from multiple interconnected graphs representing different aspects of the same data. Current research focuses on developing MGNN architectures tailored to specific applications, such as predicting outcomes from multimodal medical data or detecting illicit accounts in cryptocurrency transactions, often incorporating advanced techniques like attention mechanisms and message passing to improve performance. This approach offers significant advantages in handling complex, multifaceted data where relationships are best represented through multiple graph structures, leading to improved accuracy and efficiency in diverse fields including power grid analysis, fraud detection, and biological network modeling.

Papers

March 1, 2024

PowerFlowMultiNet: Multigraph Neural Networks for Unbalanced Three-Phase Distribution Systems
Salah Ghamizi, Jun Cao, Aoxiang Ma, Pedro Rodriguez
Multi Graph Neural Network Unbalanced Power Distribution Grid

September 4, 2023

Effective Multi-Graph Neural Networks for Illicit Account Detection on Cryptocurrency Transaction Networks
Zhihao Ding, Jieming Shi, Qing Li, Jiannong Cao
Malicious Node Multi Graph Neural Network Cryptocurrency Transaction Network Illicit Account Detection

July 13, 2023

MaxCorrMGNN: A Multi-Graph Neural Network Framework for Generalized Multimodal Fusion of Medical Data for Outcome Prediction
Niharika S. D'Souza, Hongzhi Wang, Andrea Giovannini, Antonio Foncubierta-Rodriguez, Kristen L. Beck, Orest Boyko, Tanveer Syeda-Mahmood
Multi Modality Medical Data Outcome Prediction Multimodal Electronic Health Record Modality Correlation Modality Exchange Network Multi Graph Neural Network

May 15, 2023

SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Efficient and Generalizable Protein-Protein Interaction Prediction
Ziyuan Zhao, Peisheng Qian, Xulei Yang, Zeng Zeng, Cuntai Guan, Wai Leong Tam, Xiaoli Li
High Efficiency Protein Protein Interaction Feature Correlation Graph Ensemble Multi Graph Neural Network

June 19, 2022

Geometric Matrix Completion via Sylvester Multi-Graph Neural Network
Boxin Du, Changhe Yuan, Fei Wang, Hanghang Tong
Discrete Time Matrix Completion GNN Aggregation Neural Framework Prior Network Multi Graph Neural Network

April 23, 2022

Long-term Spatio-temporal Forecasting via Dynamic Multiple-Graph Attention
Wei Shao, Zhiling Jin, Shuo Wang, Yufan Kang, Xiao Xiao, Hamid Menouar, Zhaofeng Zhang, Junshan Zhang, Flora Salim
Temporal Dependency Graph Attention Graph Fusion Graph Attention Mechanism Multi Graph Neural Network

Multi Graph Neural Network

Papers

PowerFlowMultiNet: Multigraph Neural Networks for Unbalanced Three-Phase Distribution Systems

Effective Multi-Graph Neural Networks for Illicit Account Detection on Cryptocurrency Transaction Networks

MaxCorrMGNN: A Multi-Graph Neural Network Framework for Generalized Multimodal Fusion of Medical Data for Outcome Prediction

SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Efficient and Generalizable Protein-Protein Interaction Prediction

Geometric Matrix Completion via Sylvester Multi-Graph Neural Network

Long-term Spatio-temporal Forecasting via Dynamic Multiple-Graph Attention