HP-JEPA: Hierarchical Partitioning for Multi-Resolution Graph Joint-Embedding Predictive Learning

arXiv:2608.00491 · cs.LG · Submitted 2026-08-01 · Read on arXiv

cs.LG

Submitted: 2026-08-01

Updated: 2026-09-30

Comments: 15 pages, 4 figures, 5 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 3× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Latent Space — 1× in this paper · explained in 7 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes

Sources

• Revisiting Feature Prediction for Learning Visual Representations from Video
• Representation Learning on Graphs: Methods and Applications
• Semi-Supervised Classification with Graph Convolutional Networks
• TUDataset: A collection of benchmark datasets for learning with graphs
• Deep Graph Infomax
• How Powerful are Graph Neural Networks?

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks