Stable Transformers for Graph Generation

arXiv:2609.39739 · cs.LG · Submitted 2026-09-30 · Read on arXiv

cs.LG

Submitted: 2026-09-30

Updated: 2026-09-30

Terminology

• Transformer — 1× in this paper · explained in 2 episodes

Sources

• A Note on Over-Smoothing for Graph Neural Networks
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Improving Molecular Graph Generation with Flow Matching and Optimal Transport
• Efficient Graph Generation with Graph Recurrent Attention Networks
• Advancing Graph Generation through Beta Diffusion
• Graph Neural Ordinary Differential Equations
• Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models
• A Survey on Oversmoothing in 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