EUVIMEDEUVIMED entdecken
Crossref

Graph Neural Network Meets Sparse Representation: Graph Sparse Neural Networks via Exclusive Group Lasso

Bo Jiang, Beibei Wang, Si Chen, Jin Tang, Bin Luo

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-10 · 45 (10) · 12692-12698

DOI: 10.1109/tpami.2023.3285215 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-10. Verfasst von Bo Jiang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: Major Project for New Generation of AI, National Natural Science Foundation of China, Natural Science Foundation of Anhui Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing GNNs usually conduct the layer-wise message propagation via the 'full' aggregation of all neighborhood information which are usually sensitive to the structural noises existed in the graphs, such as incorrect or undesired redundant edge connections. To overcome this issue, we propose to exploit Sparse Representation (SR) theory into GNNs and propose Graph Sparse Neural Networks (GSNNs) which conduct sparse aggregation to select reliable neighbors for message aggregation. GSNNs problem contains discrete/sparse constraint which is difficult to be optimized. Thus, we then develop a tight continuous relaxation model Exclusive Group Lasso GNNs (EGLassoGNNs) for GSNNs. An effective algorithm is derived to optimize the proposed EGLassoGNNs model. Experimental results on several benchmark datasets demonstrate the better performance and robustness of the proposed EGLassoGNNs model.

Förderung

  • Major Project for New Generation of AI
  • National Natural Science Foundation of China
  • Natural Science Foundation of Anhui Province
  • Anhui Provincial Key Research and Development Program
  • University Synergy Innovation Program of Anhui Province

Zitieren

APA

Jiang, B., Wang, B., Chen, S., Tang, J., & Luo, B. (2023). Graph Neural Network Meets Sparse Representation: Graph Sparse Neural Networks via Exclusive Group Lasso. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(10), 12692-12698. https://doi.org/10.1109/tpami.2023.3285215

Vancouver

Jiang B, Wang B, Chen S, Tang J, Luo B. Graph Neural Network Meets Sparse Representation: Graph Sparse Neural Networks via Exclusive Group Lasso. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(10):12692-12698. doi:10.1109/tpami.2023.3285215

BibTeX
@article{Jiang2023,
  author = {Jiang, Bo and Wang, Beibei and Chen, Si and Tang, Jin and Luo, Bin},
  title = {Graph Neural Network Meets Sparse Representation: Graph Sparse Neural Networks via Exclusive Group Lasso},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {10},
  pages = {12692--12698},
  doi = {10.1109/tpami.2023.3285215}
}
Kostenlos starten →