G2P xy: Generative Open-Set Node Classification on Graphs with Proxy Unknowns

doi:doi:10.57702/qunh8rqf

G2P xy: Generative Open-Set Node Classification on Graphs with Proxy Unknowns

Node classification is the task of predicting the labels of unlabeled nodes in a graph. State-of-the-art methods based on graph neural networks achieve excellent performance when all labels are available during training. But in real-life, models are often applied on data with new classes, which can lead to massive misclassification and thus significantly degrade performance.

BibTex:

@dataset{Qin_Zhang_and_Zelin_Shi_and_Xiaolin_Zhang_and_Xiaojun_Chen_and_Philippe_Fournier-Viger_and_Shirui_Pan_2024,
    abstract = {Node classification is the task of predicting the labels of unlabeled nodes in a graph. State-of-the-art methods based on graph neural networks achieve excellent performance when all labels are available during training. But in real-life, models are often applied on data with new classes, which can lead to massive misclassification and thus significantly degrade performance.},
    author = {Qin Zhang and Zelin Shi and Xiaolin Zhang and Xiaojun Chen and Philippe Fournier-Viger and Shirui Pan},
    doi = {10.57702/qunh8rqf},
    institution = {No Organization},
    keyword = {'Graph Neural Networks', 'Node Classification', 'Open-Set Classification', 'Proxy Unknowns'},
    month = {dec},
    publisher = {TIB},
    title = {G2P xy: Generative Open-Set Node Classification on Graphs with Proxy Unknowns},
    url = {https://service.tib.eu/ldmservice/dataset/g2p-xy--generative-open-set-node-classification-on-graphs-with-proxy-unknowns},
    year = {2024}
}