When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors
cs.LG, cs.AI
Submitted: 2026-10-09
Updated: 2026-10-09
Sources
- On the Power of Edge Independent Graph Models
- Prior-Informed Flow Matching for Graph Reconstruction
- Re-parameterizing VAEs for stability
- A Generalization of Transformer Networks to Graphs
- Denoising Diffusion Probabilistic Models
- Auto-Encoding Variational Bayes
- Variational Graph Auto-Encoders
- Graph Evolution: Densification and Shrinking Diameters
- Video Diffusion Models: A Survey
- Graph Diffusion that can Insert and Delete
- LGDC: Latent Graph Diffusion via Spectrum-Preserving Coarsening
- Categorical Flow Maps
- Multi-scale Attributed Node Embedding
- Random Features Strengthen Graph Neural Networks
- Principled Latent Diffusion for Graphs via Laplacian Autoencoders
- Generative Modeling by Estimating Gradients of the Data Distribution
- DiGress: Discrete Denoising diffusion for graph generation
- Flowette: Flow Matching with Graphette Priors for Graph Generation
- GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
- A Survey of Diffusion Based Image Generation Models: Issues and Their Solutions
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