Scaling Novel Graph Generation via Lightweight Structure-Guided Autoregressive Models
cs.LG, cs.AI
Submitted: 2026-06-02
Updated: 2026-09-18
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Let There Be Order: Rethinking Ordering in Autoregressive Graph Generation
- Flatten Graphs as Sequences: Transformers are Scalable Graph Generators
- RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Reinforced Self-Training (ReST) for Language Modeling
- GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generation
- GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders
- Cometh: A continuous-time discrete-state graph diffusion model
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks