← Back to all news
arXiv Machine Learning By Sirine Ayadi, Stephan G\"unnemann

H-GLow: Accelerating Graph Generation via Hazard-Guided Discrete Flow Matching

Read the original on arXiv Machine Learning →

H-Glow is a hazard‑guided framework that accelerates graph generation by decomposing Continuous‑Time Markov chain generators into hazards and conditional jump distributions. It plans graph edits and dynamically adjusts sampling time based on graph activity, allowing pretrained graph DFM models to produce higher‑quality graphs with fewer steps. The authors also propose a new graph DFM model that directly predicts hazards and conditional jumps, whose training objective cleanly splits into hazard matching and weighted jump prediction, and demonstrate its effectiveness on molecular and synthetic graph benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 9

Few-Step Generation via Data-Space Iteration

The paper introduces data‑space iteration, a few‑step generation framework that eliminates the need for a fixed probability‑flow discretization. By refining predictions directly in data space with a shared generator, each iteration is trained to produce the best possible sample within its capacity. Experiments on class‑conditional ImageNet 256×256 show that data‑space iteration outperforms standard discretization baselines and matches or improves upon schedule‑searched variants without schedule‑specific training.

By Shanchuan Lin, Yansong Peng, Fu-Yun Wang, Haoqi Fan
diffusionefficiency
More like this →