EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GMMDA: Gaussian mixture modeling of graph in latent space for graph data augmentation

Yanjin Li, Linchuan Xu, Kenji Yamanishi

Knowledge and Information Systems · 2024-12 · 66 (12) · 7667-7695

DOI: 10.1007/s10115-024-02207-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Knowledge and Information Systems, online erschienen am 29.08.2024. Verfasst von Yanjin Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Science and Technology Agency, The University of Tokyo.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph data augmentation (GDA), which manipulates graph structure and/or attributes, has been demonstrated as an effective method for improving the generalization of graph neural networks on semi-supervised node classification. As a data augmentation technique, label preservation is critical, that is, node labels should not change after data manipulation. However, most existing methods overlook the label preservation requirements. Determining the label-preserving nature of a GDA method is highly challenging, owing to the non-Euclidean nature of the graph structure. In this study, for the first time, we formulate a label-preserving problem (LPP) in the context of GDA. The LPP is formulated as an optimization problem in which, given a fixed augmentation budget, the objective is to find an augmented graph with minimal difference in data distribution compared to the original graph. To solve the LPP problem, we propose GMMDA, a generative data augmentation (DA) method based on Gaussian mixture modeling (GMM) of a graph in a latent space. We designed a novel learning objective that jointly learns a low-dimensional graph representation and estimates the GMM. The learning is followed by sampling from the GMM, and the samples are converted back to the graph as additional nodes. To uphold label preservation, we designed a minimum description length (MDL)-based method to select a set of samples that produces the minimum shift in the data distribution captured by the GMM. Through experiments, we demonstrate that GMMDA can improve the performance of graph convolutional network on Cora , Citeseer and Pubmed by as much as $$7.75\%$$ 7.75 % , $$8.75\%$$ 8.75 % and $$5.87\%$$ 5.87 % , respectively, significantly outperforming the state-of-the-art methods.

Förderung

  • Japan Science and Technology Agency
  • The University of Tokyo

Zitieren

APA

Li, Y., Xu, L., & Yamanishi, K. (2024). GMMDA: Gaussian mixture modeling of graph in latent space for graph data augmentation. Knowledge and Information Systems, 66(12), 7667-7695. https://doi.org/10.1007/s10115-024-02207-2

Vancouver

Li Y, Xu L, Yamanishi K. GMMDA: Gaussian mixture modeling of graph in latent space for graph data augmentation. Knowledge and Information Systems. 2024;66(12):7667-7695. doi:10.1007/s10115-024-02207-2

BibTeX
@article{Li2024,
  author = {Li, Yanjin and Xu, Linchuan and Yamanishi, Kenji},
  title = {GMMDA: Gaussian mixture modeling of graph in latent space for graph data augmentation},
  journal = {Knowledge and Information Systems},
  year = {2024},
  volume = {66},
  number = {12},
  pages = {7667--7695},
  doi = {10.1007/s10115-024-02207-2}
}
Kostenlos starten →