GNN Application

Graph Neural Networks (GNNs) are a powerful class of machine learning models designed to analyze and learn from data structured as graphs, addressing limitations of traditional methods on irregular data. Current research focuses on improving GNN architectures (like Graph Convolutional Networks and Graph Attention Networks), tackling challenges such as over-smoothing and heterophily, and developing robust benchmarking strategies for fair model comparison. This rapidly evolving field is impacting diverse areas, including mechanics, IoT networks, job matching, and computer vision, by enabling more accurate and efficient analysis of complex relational data. The development of larger, more diverse datasets is also a key area of ongoing work.

Papers

July 10, 2024

A review of graph neural network applications in mechanics-related domains
Yingxue Zhao, Haoran Li, Haosu Zhou, Hamid Reza Attar, Tobias Pfaff, Nan Li
Graph Drawing Narrative Review GNN Application Neural Network Application

May 27, 2024

Survey of Graph Neural Network for Internet of Things and NextG Networks
Sabarish Krishna Moorthy, Jithin Jagannath
Graph Neural Network Timely Survey State of the Art Gene Level GNN Good Thing GNN Application NextG Wireless Network

May 13, 2024

All Nodes are created Not Equal: Node-Specific Layer Aggregation and Filtration for GNN
Shilong Wang, Hao Wu, Yifan Duan, Guibin Zhang, Guohao Li, Yuxuan Liang, Shirui Pan, Kun Wang, Yang Wang
Graph Neural Network Deep Network Gene Level GNN Random Node Heterophilic Graph GNN Application Layer Aggregation Pressure Filtration

February 20, 2024

LinkSAGE: Optimizing Job Matching Using Graph Neural Networks
Ping Liu, Haichao Wei, Xiaochen Hou, Jianqiang Shen, Shihai He, Kay Qianqi Shen, Zhujun Chen, Fedor Borisyuk, Daniel Hewlett, Liang Wu, Srikant Veeraraghavan, Alex Tsun, Chengming Jiang, Wenjing Zhang
Graph Neural Network Tiltable Link Resume Job GNN Application

November 30, 2023

Utilizing Radiomic Feature Analysis For Automated MRI Keypoint Detection: Enhancing Graph Applications
Sahar Almahfouz Nasser, Shashwat Pathak, Keshav Singhal, Mohit Meena, Nihar Gupte, Ananya Chinmaya, Prateek Garg, Amit Sethi
Radiomics Feature Keypoint Detection GNN Based Retinal Image GNN Application Graph Processing

August 21, 2023

UGSL: A Unified Framework for Benchmarking Graph Structure Learning
Bahare Fatemi, Sami Abu-El-Haija, Anton Tsitsulin, Mehran Kazemi, Dustin Zelle, Neslihan Bulut, Jonathan Halcrow, Bryan Perozzi
Graph Neural Network Unified Framework Graph Structure Graph Structure Learning Deep Neural Network Parameter GNN Application

July 17, 2023

Examining the Effects of Degree Distribution and Homophily in Graph Learning Models
Mustafa Yasir, John Palowitch, Anton Tsitsulin, Long Tran-Thanh, Bryan Perozzi
Mixed Effect Synthetic Graph Graph Learning Model Benchmarking Deep Learning GNN Application Degree Distribution

February 27, 2023

IGB: Addressing The Gaps In Labeling, Features, Heterogeneity, and Size of Public Graph Datasets for Deep Learning Research
Arpandeep Khatua, Vikram Sharma Mailthody, Bhagyashree Taleka, Tengfei Ma, Xiang Song, Wen-mei Hwu
Deep Learning Manual Label Graph Benchmark Graph Datasets Large Scale Graph Datasets GNN Application

January 7, 2023

Reducing Over-smoothing in Graph Neural Networks Using Relational Embeddings
Yeskendir Koishekenov
Graph Neural Network Graph Attention Network Graph Node Undisciplined Over Smoothing Relational Embeddings GNN Application

December 20, 2022

Graph Neural Networks in Computer Vision -- Architectures, Datasets and Common Approaches
Maciej Krzywda, Szymon Łukasik, Amir H. Gandomi
Graph Neural Network Data Set Computer Vision Graph Attention Network Architecture Perspective GNN Application Different Approach

June 23, 2022

Graph Neural Networks for Temperature-Dependent Activity Coefficient Prediction of Solutes in Ionic Liquids
Jan G. Rittig, Karim Ben Hicham, Artur M. Schweidtmann, Manuel Dahmen, Alexander Mitsos
Graph Neural Network GNN Application Activity Coefficient Ionic Liquid

February 1, 2022

Investigating Transfer Learning in Graph Neural Networks
Nishai Kooverjee, Steven James, Terence van Zyl
Graph Neural Network Transfer Learning Graph Classification Synthetic Graph GNN Application

January 3, 2022

Graph Neural Networks: a bibliometrics overview
Abdalsamad Keramatfar, Mohadeseh Rafiee, Hossein Amirkhani
Graph Neural Network Bibliometric Analysis GNN Application