UnsupervisedJointk-nodeGraphRepresentations withCompositionalEnergy-BasedModels

Feb-10-2026, 09:29:58 GMT–Neural Information Processing Systems

We propose MHM-GNN, an inductive unsupervised graph representation approach that combines jointk-node representations with energy-based models (hypergraph Markov networks) and GNNs.

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

Neural Information Processing Systems

Feb-10-2026, 09:29:58 GMT

Conferences PDF

Country:
- North America
  - Canada > British Columbia
    - Metro Vancouver Regional District > Vancouver (0.04)
  - United States > Rhode Island
    - Providence County > Providence (0.04)
- South America > Brazil (0.04)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning > Statistical Learning (1.00)
  - Representation & Reasoning (0.93)

Duplicate Docs Excel Report

Title
Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models

Similar Docs Excel Report more

Title	Similarity	Source
None found