Manuscript Topics

Exploiting geometric structure has led to the development of machine learning methods which generalize better to new situations, learn using less data, and make more physically accurate predictions. Examples of geometric techniques in deep learning include graph neural networks, convolutional neural networks, equivariant neural networks, and embeddings into Reimannian manifolds. These methods incorporate constraints to preserve geometric structure such as symmetry, curvature, or distance. Geometric deep learning includes many research hotspots, such as steerable convolutions, group convolutions, tensor field networks, and hyperbolic networks. It can be widely applied in robotics, healthcare, robotics, fault diagnosis, decision analysis, motion analysis, et al.

This special issue aims to explore recent advances in geometric deep learning theory and application. We invite researchers to contribute original studies and survey papers that address theoretical, methodological, and application-driven challenges in this domain.

Topics of Interest:

• Graph-based models    
• Interpretability of geometric deep learning    
• Graph Neural Networks (GNNs)    
• Spatio-temporal graph learning    
• Non Euclidean data processing    
• Image cognitive computing    
• 3D modeling based on geometric deep learning    
• Molecular modeling based on geometric deep learning    
• Multimodal fusion techniques involving graph structures    
• Vision transformers and graph models    
• Graph-based feature learning and attention mechanisms    
• Knowledge graphs and semantic reasoning    
• Applications of geometric deep learning in computer vision, healthcare, decision analysis, and robotics

Keywords 

Graph neural networks; Graph representation learning; Geometric deep learning; Graph-based models; Knowledge graphs; Image cognitive computing

Instructions for authors
https://www.aimspress.com/era/news/solo-detail/instructionsforauthors
Please submit your manuscript to online submission system
https://aimspress.jams.pub/