We study a new research problem named semi-supervised few-shot multi-label node classification which has the following characteristics: 1) the extreme imbal-ance between the number of labeled and unlabeled nodes that are connected on graphs (handled by semi-supervised node learning); 2) the few labeled nodes per label (few-shot learning); and 3) the semantical correlations among labels for they share the same subsets of nodes (multi-label classification). In this paper, we propose a Label-Aware Representation Network (LARN) model to tackle this problem, by taking advantage of the semantic knowledge of labels to characterize nodes and their neighbors. Such a label-aware feature learning process allows a node to prepare its representation by knowing how it will be classified. The learned rich representations so can combat the scarcity of labeled training nodes. A label correlation scanner is then proposed to adaptively capture the label correlation and extract the useful information to generate the final node representation. Experimental results demonstrate that LARN consistently out- performs the state-of-the-art methods with significant margins, especially when only a few-shot labeled nodes are available.
Bibliographical noteKAUST Repository Item: Exported on 2022-01-18
Acknowledged KAUST grant number(s): FCC/1/1976-19-01
Acknowledgements: This work was supported in part by the Fundamental Research Funds for the Central Universities(2019YJS050); The National Natural Science Foundation of China under Grant 61822601, 61773050, 61632004 and 61828302; The Beijing Natural Science Foundation under Grant Z180006; National Key Research and Development Program (2017YFC1703506); The Fundamental Research Funds for the Central Universities (2019JBZ110); And King Abdullah University of ScienceTechnology, under award number FCC/1/1976-19-01.
ASJC Scopus subject areas
- Artificial Intelligence
- Theoretical Computer Science
- Information Systems and Management
- Control and Systems Engineering
- Computer Science Applications