Results 81 to 90 of about 748,129 (177)

Node Classification With Integrated Reject Option

CoRR
One of the key tasks in graph learning is node classification. While Graph neural networks have been used for various applications, their adaptivity to reject option setting is not previously explored. In this paper, we propose NCwR, a novel approach to node classification in Graph Neural Networks (GNNs) with an integrated reject option, which allows ...
Uday Bhaskar, Jayadratha Gayen, Charu Sharma, Naresh Manwani   +3 more
openaire   +2 more sources

Heterogeneous Graph Neural Network Model Based on Edge Feature Generation and Meta-Graph Similarity for Feature Extraction

IEEE Access
Edges and nodes form the core elements of heterogeneous graphs (HGs). However, existing heterogeneous graph neural networks (HGNNS) largely rely on meta-paths to capture semantic information of nodes, often overlooking the features embedded in edges ...
Chengyuan Qian
doaj   +1 more source

Path-enhanced graph convolutional networks for node classification without features. [PDF]

PLoS One, 2023
Jiao Q, Zhao P, Zhang H, Han Y, Liu G.
europepmc   +1 more source

Finding Counterfactual Evidences for Node Classification

Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2
Accepted by KDD ...
Dazhuo Qiu, Jinwen Chen, Arijit Khan, Yan Zhao, Francesco Bonchi   +4 more
openaire   +2 more sources

The Role of AI in Breast Cancer Lymph Node Classification: A Comprehensive Review. [PDF]

Cancers (Basel), 2023
Vrdoljak J, Krešo A, Kumrić M, Martinović D, Cvitković I, Grahovac M, Vickov J, Bukić J, Božic J.   +8 more
europepmc   +1 more source

A BERT-GNN Approach for Metastatic Breast Cancer Prediction Using Histopathology Reports

Diagnostics
Metastatic breast cancer (MBC) continues to be a leading cause of cancer-related deaths among women. This work introduces an innovative non-invasive breast cancer classification model designed to improve the identification of cancer metastases.
Abdullah Basaad , Shadi Basurra , Edlira Vakaj , Ahmed Karam Eldaly , Mohammed M. Abdelsamea    +4 more
doaj   +1 more source

Federated Node Classification over Graphs with Latent Link-type Heterogeneity. [PDF]

Proc Int World Wide Web Conf, 2023
Xie H, Xiong L, Yang C.
europepmc   +1 more source

Posterior Label Smoothing for Node Classification

Proceedings of the AAAI Conference on Artificial Intelligence
Label smoothing is a widely studied regularization technique in machine learning. However, its potential for node classification in graph-structured data, spanning homophilic to heterophilic graphs, remains largely unexplored. We introduce posterior label smoothing, a novel method for transductive node classification that derives soft labels from a ...
Jaeseung Heo, Moonjeong Park, Dongwoo Kim 0002   +2 more
openaire   +2 more sources

G-MLP: Graph Multi-Layer Perceptron for Node Classification Using Contrastive Learning

IEEE Access
Graph Convolutional Network (GCN) and its variants emerged as powerful graph deep learning methods with promising performance on graph analysis tasks. Different variants improve performance by introducing efficient information propagation and aggregation
Lining Yuan, Ping Jiang, Wenlei Hou, Wanyan Huang   +3 more
doaj   +1 more source

Self-Supervised Node Classification with Strategy and Actively Selected Labeled Set. [PDF]

Entropy (Basel), 2022
Kang Y, Liu K, Cao Z, Zhang J.
europepmc   +1 more source