Graph neural networks: Taxonomy, advances, and trends

Y Zhou, H Zheng, X Huang, S Hao, D Li… - ACM Transactions on …, 2022 - dl.acm.org
Graph neural networks provide a powerful toolkit for embedding real-world graphs into low-
dimensional spaces according to specific tasks. Up to now, there have been several surveys …

Gated graph recurrent neural networks

L Ruiz, F Gama, A Ribeiro - IEEE Transactions on Signal …, 2020 - ieeexplore.ieee.org
Graph processes exhibit a temporal structure determined by the sequence index and and a
spatial structure determined by the graph support. To learn from graph processes, an …

Spatio-temporal graph convolutional networks via view fusion for trajectory data analytics

W Hu, W Li, X Zhou, A Kawai, K Fueda… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
Trajectory data contains rich spatial and temporal information. Turning trajectories into
graphs and then analyzing them efficiently in an AI-empowered way is a representative …

Graph neural network for robust public transit demand prediction

C Li, L Bai, W Liu, L Yao… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Understanding and forecasting mobility patterns and travel demand are fundamental and
critical to efficient transport infrastructure planning and service operation. However, most …

Adaptive graph convolutional collaboration networks for semi-supervised classification

S Fu, S Wang, W Liu, B Liu, B Zhou, X You, Q Peng… - Information …, 2022 - Elsevier
Graph convolution networks (GCNs) have achieved remarkable success in processing non-
Euclidean data. GCNs update the feature representations of each sample by aggregating …

Text semantic fusion relation graph reasoning for few-shot object detection on remote sensing images

S Zhang, F Song, X Liu, X Hao, Y Liu, T Lei, P Jiang - Remote Sensing, 2023 - mdpi.com
Most object detection methods based on remote sensing images are generally dependent
on a large amount of high-quality labeled training data. However, due to the slow acquisition …

A practical tutorial on graph neural networks

IR Ward, J Joyner, C Lickfold, Y Guo… - ACM Computing …, 2022 - dl.acm.org
Graph neural networks (GNNs) have recently grown in popularity in the field of artificial
intelligence (AI) due to their unique ability to ingest relatively unstructured data types as …

Interference recommendation for the pump sizing process in progressive cavity pumps using graph neural networks

L Starke, AF Hoppe, A Sartori, SF Stefenon… - Scientific Reports, 2023 - nature.com
Pump sizing is the process of dimensional matching of an impeller and stator to provide a
satisfactory performance test result and good service life during the operation of progressive …

Mathematical word problem generation from commonsense knowledge graph and equations

T Liu, Q Fang, W Ding, H Li, Z Wu, Z Liu - arxiv preprint arxiv:2010.06196, 2020 - arxiv.org
There is an increasing interest in the use of mathematical word problem (MWP) generation
in educational assessment. Different from standard natural question generation, MWP …

Hypergraph representation for detecting 3D objects from noisy point clouds

P Jiang, X Deng, L Wang, Z Chen… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
It is challenging to detect 3D objects from noise point clouds by Graph Neural Networks
(GNNs), though graph-based methods have shown promising results in 3D classifications …