Graph Decipher: A transparent dual‐attention graph neural network to understand the message‐passing mechanism for the node classification
Sign Up to like & getrecommendations! Published in 2022 at "International Journal of Intelligent Systems"
DOI: 10.1002/int.22966
Abstract: Graph neural networks (GNNs) can be effectively applied to solve many real‐world problems across widely diverse fields. Their success is inseparable from the message‐passing mechanisms evolving over the years. However, current mechanisms treat all node… read more here.
Keywords: node classification; message passing; graph; graph neural ... See more keywords
Node classification over bipartite graphs through projection
Sign Up to like & getrecommendations! Published in 2020 at "Machine Learning"
DOI: 10.1007/s10994-020-05898-0
Abstract: Many real-world large datasets correspond to bipartite graph data settings—think for example of users rating movies or people visiting locations. Although there has been some prior work on data analysis with such bigraphs, no general… read more here.
Keywords: bipartite graphs; classification; classification bipartite; projection ... See more keywords
Nishimori meets Bethe: a spectral method for node classification in sparse weighted graphs
Sign Up to like & getrecommendations! Published in 2021 at "Journal of Statistical Mechanics: Theory and Experiment"
DOI: 10.1088/1742-5468/ac21d3
Abstract: This article unveils a new relation between the Nishimori temperature parametrizing a distribution P and the Bethe free energy on random Erdős–Rényi graphs with edge weights distributed according to P. Estimating the Nishimori temperature being… read more here.
Keywords: method node; method; nishimori temperature; spectral method ... See more keywords
Minority-Weighted Graph Neural Network for Imbalanced Node Classification in Social Networks of Internet of People
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Internet of Things Journal"
DOI: 10.1109/jiot.2022.3200964
Abstract: Social networks are an essential component of the Internet of People (IoP) and play an important role in stimulating interactive communication among people. Graph convolutional networks provide methods for social network analysis with its impressive… read more here.
Keywords: network; classification; social networks; graph neural ... See more keywords
Self-Paced Co-Training of Graph Neural Networks for Semi-Supervised Node Classification.
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2022.3157688
Abstract: Graph neural networks (GNNs) have demonstrated great success in many graph data-based applications. The impressive behavior of GNNs typically relies on the availability of a sufficient amount of labeled data for model training. However, in… read more here.
Keywords: neural networks; training; semi supervised; self paced ... See more keywords
Neighborhood Pattern Is Crucial for Graph Convolutional Networks Performing Node Classification.
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2022.3229721
Abstract: Graph convolutional networks (GCNs) are widely believed to perform well in the graph node classification task, and homophily assumption plays a core rule in the design of previous GCNs. However, some recent advances on this… read more here.
Keywords: topology; graph convolutional; convolutional networks; graph ... See more keywords
Tackling Over-Smoothing in Graph Convolutional Networks With EM-Based Joint Topology Optimization and Node Classification
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Signal and Information Processing over Networks"
DOI: 10.1109/tsipn.2023.3244112
Abstract: Over-smoothing has emerged as a severe obstacle to node classification with message passing based graph convolutional networks (GCNs). Classification performance dramatically deteriorates for deep GCNs, as message passing over the observed noisy graph topology cannot… read more here.
Keywords: topology; graph convolutional; topology optimization; classification ... See more keywords
GRNN: Graph-Retraining Neural Network for Semi-Supervised Node Classification
Sign Up to like & getrecommendations! Published in 2023 at "Algorithms"
DOI: 10.3390/a16030126
Abstract: In recent years, graph neural networks (GNNs) have played an important role in graph representation learning and have successfully achieved excellent results in semi-supervised classification. However, these GNNs often neglect the global smoothing of the… read more here.
Keywords: network; classification; semi supervised; graph ... See more keywords
Scalably Using Node Attributes and Graph Structure for Node Classification
Sign Up to like & getrecommendations! Published in 2022 at "Entropy"
DOI: 10.3390/e24070906
Abstract: The task of node classification concerns a network where nodes are associated with labels, but labels are known only for some of the nodes. The task consists of inferring the unknown labels given the known… read more here.
Keywords: structure; scalably using; classification; using node ... See more keywords