Temporal Heterogeneous Graph Pretraining for Relational Deep Learning

arXiv:2609.35219 · cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Heterogeneous Graph — 1× in this paper · explained in 2 episodes

Sources

• RelGNN: Composite Message Passing for Relational Deep Learning
• Do We Really Need Complicated Model Architectures For Temporal Networks?
• Temporal Graph Pattern Machine
• THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model
• RoFormer: Enhanced Transformer with Rotary Position Embedding
• Representation Learning with Contrastive Predictive Coding
• RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases

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