← Back to all news
arXiv Machine Learning

Unrestrained Simplex Denoising for Discrete Data. A Non-Markovian Approach Applied to Graph Generation

The paper introduces simplex denoising, a generative framework that operates on the probability simplex rather than directly in the discrete state space. It employs a non‑Markovian noising scheme where noisy representations at different times are conditionally independent, preserving theoretical guarantees while removing unnecessary constraints. Empirical results show that unrestrained simplex denoising outperforms strong discrete diffusion and flow‑matching baselines on both synthetic and real‑world graph benchmarks.

Related stories

arXiv AI
Oct 12

When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors

The paper identifies a limitation of discrete graph diffusion models: independent edge updates combined with exchangeability force the terminal prior to be an Erdős–Rényi graph, which hampers denoising and leads to loss of node heterogeneity. To overcome this, the authors propose a Latent Sociability Prior (LSP) and a joint diffusion process that co‑evolves latent sociability variables with graph structure, eliminating edge independence while maintaining exchangeability. Experiments on several graph generation datasets show that this approach better captures graph distributions than baseline methods that lack node features.

By Adarsh Jamadandi, Nicolas Keriven, Aline Roumy
diffusion
More like this →
arXiv Computation and Language
Oct 1

Simplex Relaxation for Discrete Diffusion

arXiv:2608.10615v2 Announce Type: replace Abstract: Discrete diffusion models for categorical generation are defined by a corruption kernel, which determines the intermediate state space and the asso...

By Jinya Sakurai, Patrick Pynadath, Satoshi Hayakawa, Jaehong Yoon, Xulei Yang, Nancy F. Chen, Xun Xu
diffusion
More like this →
arXiv Machine Learning
Jun 2

Consistent Diffusion Language Models

arXiv:2605. 00161v2 Announce Type: replace Abstract: Diffusion language models (DLMs) are an attractive alternative to autoregressive models because they promise sublinear-time, parallel generation, yet practical gains remain elusive as high-quality samples still demand hundreds of refinement steps.

By Hasan Amin, Yuan Gao, Yaser Souri, Subhojit Som, Ming Yin, Rajiv Khanna, Xia Song
llmsdiffusionefficiency
More like this →
arXiv Machine Learning
Sep 24

Variational Bayesian Flow Network for Graph Generation

The paper introduces Variational Bayesian Flow Network (VBFN), a graph generation model that lifts Bayesian updates to a joint Gaussian belief family with structured precisions, enabling coupled node and edge updates in a single fusion step. By constructing sample‑agnostic sparse precisions from a representation‑induced dependency graph, VBFN avoids label leakage while enforcing node‑edge consistency. Experiments on synthetic and molecular graph datasets show that VBFN improves fidelity and diversity over baseline methods.

By Yida Xiong, Jiameng Chen, Xiuwen Gong, Jia Wu, Shirui Pan, Wenbin Hu
diffusion
More like this →
arXiv Machine Learning
Sep 25

From Graphs to Feeders: Constraint-Guided Diffusion for Rule-Compliant Feeder Generation

The paper introduces PG‑DiGress, a constraint‑guided discrete denoising diffusion model that generates power‑grid feeder topologies while respecting electrical compatibility and radiality rules. By injecting feeder constraints as soft masks during the reverse diffusion process and applying a final projection step, the model learns categorical node and edge patterns from existing feeder data. Evaluation shows a dramatic improvement in rule compliance, raising the strict feeder pass rate from 13.7% to 96.8%, and the generated graphs can be converted into executable feeder models for downstream analysis.

By Yu Qin, Andrew Glaws, Aadil Latif, Ryan King
diffusion
More like this →
arXiv Machine Learning
Jul 24

Expanding Flow Maps

arXiv:2607. 21585v1 Announce Type: new Abstract: Flow-based generative models have enabled remarkable progress in fast and controllable generation across continuous and discrete state spaces, yet existing parameterizations are constrained to fixed dimensions or fixed sequence lengths.

By Sophia Tang, Pranam Chatterjee
More like this →