Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology

Nima Dehmamy, Albert-Laszlo Barabasi, Rose Yu

Feb-19-2026, 16:35:44 GMT–Neural Information Processing Systems

Without careful design, GCNs can fail miserably even with multiple layers and nonlinear activation functions.

artificial intelligence, arxivpreprintarxiv, machine learning, (18 more...)

Neural Information Processing Systems

Feb-19-2026, 16:35:44 GMT

Conferences PDF

Country:
- North America
  - United States
    - Massachusetts > Suffolk County
      - Boston (0.05)
    - Illinois > Cook County
      - Evanston (0.04)
  - Canada > British Columbia
    - Metro Vancouver Regional District > Vancouver (0.04)
- Europe > Hungary
  - Budapest > Budapest (0.04)

Industry:
- Health & Medicine (0.69)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (1.00)

Duplicate Docs Excel Report

Title
Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology

Similar Docs Excel Report more

Title	Similarity	Source
None found