Skip to main content

Learning Disentangled Graph Convolutional Networks Locally and Globally.

Publication ,  Journal Article
Guo, J; Huang, K; Yi, X; Zhang, R
Published in: IEEE transactions on neural networks and learning systems
March 2024

Graph convolutional networks (GCNs) emerge as the most successful learning models for graph-structured data. Despite their success, existing GCNs usually ignore the entangled latent factors typically arising in real-world graphs, which results in nonexplainable node representations. Even worse, while the emphasis has been placed on local graph information, the global knowledge of the entire graph is lost to a certain extent. In this work, to address these issues, we propose a novel framework for GCNs, termed LGD-GCN, taking advantage of both local and global information for disentangling node representations in the latent space. Specifically, we propose to represent a disentangled latent continuous space with a statistical mixture model, by leveraging neighborhood routing mechanism locally. From the latent space, various new graphs can then be disentangled and learned, to overall reflect the hidden structures with respect to different factors. On the one hand, a novel regularizer is designed to encourage interfactor diversity for model expressivity in the latent space. On the other hand, the factor-specific information is encoded globally via employing a message passing along these new graphs, in order to strengthen intrafactor consistency. Extensive evaluations on both synthetic and five benchmark datasets show that LGD-GCN brings significant performance gains over the recent competitive models in both disentangling and node classification. Particularly, LGD-GCN is able to outperform averagely the disentangled state-of-the-arts by 7.4% on social network datasets.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

IEEE transactions on neural networks and learning systems

DOI

EISSN

2162-2388

ISSN

2162-237X

Publication Date

March 2024

Volume

35

Issue

3

Start / End Page

3640 / 3651

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 4602 Artificial intelligence
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Guo, J., Huang, K., Yi, X., & Zhang, R. (2024). Learning Disentangled Graph Convolutional Networks Locally and Globally. IEEE Transactions on Neural Networks and Learning Systems, 35(3), 3640–3651. https://doi.org/10.1109/tnnls.2022.3195336
Guo, Jingwei, Kaizhu Huang, Xinping Yi, and Rui Zhang. “Learning Disentangled Graph Convolutional Networks Locally and Globally.IEEE Transactions on Neural Networks and Learning Systems 35, no. 3 (March 2024): 3640–51. https://doi.org/10.1109/tnnls.2022.3195336.
Guo J, Huang K, Yi X, Zhang R. Learning Disentangled Graph Convolutional Networks Locally and Globally. IEEE transactions on neural networks and learning systems. 2024 Mar;35(3):3640–51.
Guo, Jingwei, et al. “Learning Disentangled Graph Convolutional Networks Locally and Globally.IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 3, Mar. 2024, pp. 3640–51. Epmc, doi:10.1109/tnnls.2022.3195336.
Guo J, Huang K, Yi X, Zhang R. Learning Disentangled Graph Convolutional Networks Locally and Globally. IEEE transactions on neural networks and learning systems. 2024 Mar;35(3):3640–3651.

Published In

IEEE transactions on neural networks and learning systems

DOI

EISSN

2162-2388

ISSN

2162-237X

Publication Date

March 2024

Volume

35

Issue

3

Start / End Page

3640 / 3651

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 4602 Artificial intelligence