Results 141 to 150 of about 748,129 (177)
Some of the next articles are maybe not open access.
Progressive Supervision for Node Classification
2021Graph Convolution Networks (GCNs) are a powerful approach for the task of node classification, in which GCNs are trained by minimizing the loss over the final-layer predictions. However, a limitation of this training scheme is that it enforces every node to be classified from the fixed and unified size of receptive fields, which may not be optimal.
Yiwei Wang 0001 +4 more
openaire +2 more sources
Label-dependent node classification in the network
Neurocomputing, 2012Relations between objects in various systems, such as hyperlinks connecting web pages, citations of scientific papers, conversations via email or social interactions in Web 2.0 portals are commonly modeled by networks. One of many interesting problems currently studied for such domains is node classification. Due to the nature of the networked data and
Przemyslaw Kazienko, Tomasz Kajdanowicz
openaire +1 more source
Extending the classification of nodes in social networks
Proceedings of 2011 IEEE International Conference on Intelligence and Security Informatics, 2011Because of computational concerns, social network analysis generally uses only directly connected nodes to perform classification tasks. However, recent research indicates that this method of classification may not consider that nodes in the graph could have different influence over other nodes near them in the graph.
Raymond Heatherly, Murat Kantarcioglu
openaire +1 more source
Using node relationships for hierarchical classification
2016 IEEE International Conference on Image Processing (ICIP), 2016Hierarchical classification is a computational efficient approach for large-scale image classification. The main challenging issue of this approach is to deal with error propagation. Irrelevant branching decision made at a parent node cannot be corrected at its child nodes in traversing the tree for classification.
Tien-Dung Mai +5 more
openaire +1 more source
Hashing Graph Convolution for Node Classification
Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019Convolution on graphs has aroused great interest in AI due to its potential applications to non-gridded data. To bypass the influence of ordering and different node degrees, the summation/average diffusion/aggregation is often imposed on local receptive field in most prior works.
Wenting Zhao 0001 +5 more
openaire +1 more source
Feature Analysis and Classification of Lymph Nodes
2010Pathological changes in lymph nodes (LN) can be diagnosed using biopsy, which is a time consuming process. Compared to biopsy, sonography is a better material for detecting pathology in the LN. However, there is lack of consistency between different ultrasound systems, which tend to produce images with different properties.
Chuan-Yu Chang +2 more
openaire +1 more source
Generalized Few-Shot Node Classification
2022 IEEE International Conference on Data Mining (ICDM), 2022Zhe Xu 0007 +4 more
openaire +1 more source
A graph neural network-based node classification model on class-imbalanced graph data
Knowledge-Based Systems, 2022Zhenhua Huang
exaly
Enhancing Graph Neural Networks via auxiliary training for semi-supervised node classification
Knowledge-Based Systems, 2021Yu Song, Xing Xie, Hai Jin
exaly