Results 31 to 40 of about 9,290 (165)

Atomistic Line Graph Neural Network for improved materials property predictions

open access: yesnpj Computational Materials, 2021
Graph neural networks (GNN) have been shown to provide substantial performance improvements for atomistic material representation and modeling compared with descriptor-based machine learning models.
Kamal Choudhary, Brian DeCost
doaj   +1 more source

Ego-GNNs: Exploiting Ego Structures in Graph Neural Networks [PDF]

open access: yesICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
Graph neural networks (GNNs) have achieved remarkable success as a framework for deep learning on graph-structured data. However, GNNs are fundamentally limited by their tree-structured inductive bias: the WL-subtree kernel formulation bounds the representational capacity of GNNs, and polynomial-time GNNs are provably incapable of recognizing triangles
Dylan Sandfelder   +2 more
openaire   +3 more sources

MAG-GNN: Reinforcement Learning Boosted Graph Neural Network

open access: yesAdvances in Neural Information Processing Systems 36, 2023
Accepted to NeurIPS ...
Lecheng Kong   +5 more
openaire   +4 more sources

Graph Neural Networks Using Local Descriptions in Attributed Graphs: An Application to Symbol Recognition and Hand Written Character Recognition

open access: yesIEEE Access, 2021
Graph-based methods have been widely used by the document image analysis and recognition community, as the different objects and the content in document images is best represented by this powerful structural representation. Designing of novel computation
Nadeem Iqbal Kajla   +3 more
doaj   +1 more source

Explicit Feature Interaction-Aware Graph Neural Network

open access: yesIEEE Access
Graph neural networks (GNNs) are powerful tools for handling graph-structured data. However, their design often limits them to learning only higher-order feature interactions, leaving low-order feature interactions overlooked. To address this problem, we
Minkyu Kim, Hyun-Soo Choi, Jinho Kim
doaj   +1 more source

Image classification method based on superpixels and Graph Neural Network [PDF]

open access: yesITM Web of Conferences
In image classification tasks, commonly used deep learning network architectures include Convolutional Neural Network (CNN) and Vision Transformer (ViT).
Tang Yonghong
doaj   +1 more source

Graph Anomaly Detection With Graph Neural Networks: Current Status and Challenges

open access: yesIEEE Access, 2022
Graphs are used widely to model complex systems, and detecting anomalies in a graph is an important task in the analysis of complex systems. Graph anomalies are patterns in a graph that do not conform to normal patterns expected of the attributes and/or ...
Hwan Kim   +3 more
doaj   +1 more source

Graph Isomorphism and Hybrid-Order Residual Gated Graph Neural Network for Session-Based Recommendation [PDF]

open access: yesJisuanji kexue yu tansuo
Session-based recommendation aims to predict which item will be clicked next for the current session. Aiming at the shortcomings of existing session recommendation models based on graph neural network, this paper proposes a model named graph isomorphism ...
WANG Yonggui, YU Qi
doaj   +1 more source

Protein Docking Model Evaluation by Graph Neural Networks

open access: yesFrontiers in Molecular Biosciences, 2021
Physical interactions of proteins play key functional roles in many important cellular processes. To understand molecular mechanisms of such functions, it is crucial to determine the structure of protein complexes.
Xiao Wang   +3 more
doaj   +1 more source

DiP-GNN: Discriminative Pre-Training of Graph Neural Networks

open access: yesCoRR, 2022
Graph neural network (GNN) pre-training methods have been proposed to enhance the power of GNNs. Specifically, a GNN is first pre-trained on a large-scale unlabeled graph and then fine-tuned on a separate small labeled graph for downstream applications, such as node classification.
Simiao Zuo   +5 more
openaire   +3 more sources

Home - About - Disclaimer - Privacy