M2m GNN

M2M GNNs represent a class of graph neural networks designed to address limitations in handling complex graph structures, particularly those exhibiting heterophily (where connected nodes have dissimilar labels). Current research focuses on improving model robustness to noise and missing data, enhancing explainability through self-explaining architectures and incorporating domain knowledge (e.g., physical rules), and developing more efficient and scalable algorithms for large graphs. These advancements are significant for various applications, including improved accuracy in tasks like link prediction, node classification, and time-series forecasting on graph-structured data, as well as enabling more reliable uncertainty quantification in predictions.

Papers

September 27, 2024

Positional Encoder Graph Quantile Neural Networks for Geographic Data
William E. R. de Amorim, Scott A. Sisson, T. Rodrigues, David J. Nott, Guilherme S. Rodrigues
Quantile Regression Geospatial Data M2m GNN

September 3, 2024

Physical Rule-Guided Convolutional Neural Network
Kishor Datta Gupta, Marufa Kamal, Rakib Hossain Rifat, Mohd Ariful Haque, Roy George
Convolutional Neural Network Physic Informed CNN Performance M2m GNN

August 14, 2024

Towards Few-shot Self-explaining Graph Neural Networks
Jingyu Peng, Qi Liu, Linan Yue, Zaixi Zhang, Kai Zhang, Yunhao Sha
Explanation Generation GNN Explanation Self Explaining M2m GNN Self Explainable Graph Neural Network

June 12, 2024

Heuristic Learning with Graph Neural Networks: A Unified Framework for Link Prediction
Juzheng Zhang, Lanning Wei, Zhen Xu, Quanming Yao
Graph Neural Network Unified Framework Link Prediction Graph Learning Heuristic Learning M2m GNN Neural Network Heuristic Search With Amortized Value Estimates"

May 31, 2024

Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs
Langzhang Liang, Sunwoo Kim, Kijung Shin, Zenglin Xu, Shirui Pan, Yuan Qi
LeArning Abstract Graph Neural Network Heterophilic Graph Homophilous Graph Cultural Sign M2m GNN

May 7, 2024

Adaptive Least Mean pth Power Graph Neural Networks
Changran Peng, Yi Yan, Ercan E. Kuruoglu
Adaptive Importance Graph Signal Adaptive Filter M2m GNN

January 31, 2024

PF-GNN: Differentiable particle filtering based approximation of universal graph representations
Mohammed Haroon Dupty, Yanfei Dong, Wee Sun Lee
Graph Neural Network Graph Representation Average Approximation Graph Isomorphism Differentiable Particle Filter M2m GNN

July 31, 2023

TFE-GNN: A Temporal Fusion Encoder Using Graph Neural Networks for Fine-grained Encrypted Traffic Classification
Haozhen Zhang, Le Yu, Xi Xiao, Qing Li, Francesco Mercaldo, Xiapu Luo, Qixu Liu
Graph Neural Network Traffic Classification Temporal Encoder Encrypted Traffic Classification M2m GNN

November 16, 2022

PU GNN: Chargeback Fraud Detection in P2E MMORPGs via Graph Attention Networks with Imbalanced PU Labels
Jiho Choi, Junghoon Park, Woocheol Kim, Jin-Hyeok Park, Yumin Suh, Minchang Sung
Graph Attention Network Fraud Detection Credit Card Fraud Detection M2m GNN Imbalanced Dataset Multiplayer Online Battle Arena

May 20, 2022

Diagnosis and Prognosis of COVID-19 Disease Using Routine Blood Values and LogNNet Neural Network
Mehmet Tahir Huyut, Andrei Velichko
Covid 19 Medical Diagnosis Prognosis Prediction M2m GNN

May 17, 2022

KGNN: Distributed Framework for Graph Neural Knowledge Representation
Binbin Hu, Zhiyang Hu, Zhiqiang Zhang, Jun Zhou, Chuan Shi
Knowledge Graph New Framework GNN Cl M2m GNN Knowledge Representation Learning

May 10, 2022

A Neural Network Architecture for Program Understanding Inspired by Human Behaviors
Renyu Zhu, Lei Yuan, Xiang Li, Ming Gao, Wenyuan Cai
Neural Network Architecture Human Behavior Code Representation Code Clone Detection M2m GNN Program Comprehension

March 7, 2022

HAR-GCNN: Deep Graph CNNs for Human Activity Recognition From Highly Unlabeled Mobile Sensor Data
Abduallah Mohamed, Fernando Lejarza, Stephanie Cahail, Christian Claudel, Edison Thomaz
Activity Recognition Sensor Data Temporal Relation Graph Convolutional M2m GNN Activity Label

January 5, 2022

GLAN: A Graph-based Linear Assignment Network
He Liu, Tao Wang, Congyan Lang, Songhe Feng, Yi Jin, Yidong Li
Differentiable Solver Linear Assignment M2m GNN

November 14, 2021

$p$-Laplacian Based Graph Neural Networks
Guoji Fu, Peilin Zhao, Yatao Bian
Graph Neural Network State of the Art Heterophilic Graph Semi Supervised Node Classification M2m GNN Polynomial Graph Filter

M2m GNN

Papers

Positional Encoder Graph Quantile Neural Networks for Geographic Data

Physical Rule-Guided Convolutional Neural Network

Towards Few-shot Self-explaining Graph Neural Networks

Heuristic Learning with Graph Neural Networks: A Unified Framework for Link Prediction

Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs

Adaptive Least Mean pth Power Graph Neural Networks

PF-GNN: Differentiable particle filtering based approximation of universal graph representations

TFE-GNN: A Temporal Fusion Encoder Using Graph Neural Networks for Fine-grained Encrypted Traffic Classification

PU GNN: Chargeback Fraud Detection in P2E MMORPGs via Graph Attention Networks with Imbalanced PU Labels

Diagnosis and Prognosis of COVID-19 Disease Using Routine Blood Values and LogNNet Neural Network

KGNN: Distributed Framework for Graph Neural Knowledge Representation

A Neural Network Architecture for Program Understanding Inspired by Human Behaviors

HAR-GCNN: Deep Graph CNNs for Human Activity Recognition From Highly Unlabeled Mobile Sensor Data

GLAN: A Graph-based Linear Assignment Network

$p$-Laplacian Based Graph Neural Networks