Results 41 to 50 of about 24,295 (253)

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

CoRR, 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, Haoming Jiang, Qingyu Yin, Xianfeng Tang, Bing Yin, Tuo Zhao   +5 more
openaire   +2 more sources

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

Jisuanji 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

Graph Few-shot Learning via Knowledge Transfer

, 2020
Towards the challenging problem of semi-supervised node classification, there have been extensive studies. As a frontier, Graph Neural Networks (GNNs) have aroused great interest recently, which update the representation of each node by aggregating ...
Chawla, Nitesh V., Huang, Junzhou, Jiang, Meng, Li, Zhenhui, Wang, Suhang, Wei, Ying, Yao, Huaxiu, Zhang, Chuxu   +7 more
core   +1 more source

MAG-GNN: Reinforcement Learning Boosted Graph Neural Network

Advances in Neural Information Processing Systems 36, 2023
Accepted to NeurIPS ...
Lecheng Kong, Jiarui Feng, Hao Liu 0057, Dacheng Tao, Yixin Chen 0001, Muhan Zhang   +5 more
openaire   +3 more sources

Protein Docking Model Evaluation by Graph Neural Networks

Frontiers 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, Sean T. Flannery, Daisuke Kihara, Daisuke Kihara   +3 more
doaj   +1 more source

Explicit Feature Interaction-Aware Graph Neural Network

IEEE 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

A graph neural network-based bearing fault detection method

Scientific Reports, 2023
Bearings are very important components in mechanical equipment, and detecting bearing failures helps ensure healthy operation of mechanical equipment and can prevent catastrophic accidents.
Lu Xiao, Xiaoxin Yang, Xiaodong Yang
doaj   +1 more source

An Enhanced GNN Encoder-Based Approach to the Vehicle Routing Problem With Task Priority and Limited Resources

IEEE Access
This study proposes a novel approach to the Vehicle Routing Problem with Task Priority and Limited Resources (VRPTPLR) by leveraging a Graph Neural Network (GNN) encoder.
Kwangcheol Shin, Uyanga Otgonbayar, Youngmi Kim   +2 more
doaj   +1 more source

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

IEEE 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, Byung Suk Lee, Won-Yong Shin, Sungsu Lim   +3 more
doaj   +1 more source

MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions

, 2019
Predicting interactions between structured entities lies at the core of numerous tasks such as drug regimen and new material design. In recent years, graph neural networks have become attractive.
Chen, Long, Tao, Jing, Wang, Pinghui, Xu, Nuo, Zhao, Junzhou   +4 more
core   +1 more source