An Analysis of Role Semantics in Directed Dynamic Graph Modeling for Edge Classification

arXiv:2602.23135 · cs.LG, cs.AI, cs.SI · Submitted 2026-02-26 · Read on arXiv

cs.LG, cs.AI, cs.SI

Submitted: 2026-02-26

Updated: 2026-10-12

Code: https://github.com/zjs123/DTGB3https:

Terminology

• Alignment — 2× in this paper · explained in 1 episode
• Directional Role Alignment — 1× in this paper
• Representation Learning — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Temporal Graph Networks for Deep Learning on Dynamic Graphs
• TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning
• Gaussian Error Linear Units (GELUs)
• Representation Learning with Contrastive Predictive Coding

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