Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.00236 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917375923716096 |
|---|---|
| author | Boget, Yoann Strasser, Pablo Kalousis, Alexandros |
| author_facet | Boget, Yoann Strasser, Pablo Kalousis, Alexandros |
| contents | Denoising-based models, including diffusion and flow matching, have led to substantial advances in graph generation. Despite this progress, such models remain constrained by two fundamental limitations: a computational cost that scales quadratically with the number of nodes and a large number of function evaluations required during generation. In this work, we introduce a novel hierarchical generative framework that reduces the number of node pairs that must be evaluated and adopts discrete flow matching to significantly decrease the number of denoising iterations. We empirically demonstrate that our approach more effectively captures graph distributions while substantially reducing generation time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00236 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Hierarchical Discrete Flow Matching for Graph Generation Boget, Yoann Strasser, Pablo Kalousis, Alexandros Machine Learning Denoising-based models, including diffusion and flow matching, have led to substantial advances in graph generation. Despite this progress, such models remain constrained by two fundamental limitations: a computational cost that scales quadratically with the number of nodes and a large number of function evaluations required during generation. In this work, we introduce a novel hierarchical generative framework that reduces the number of node pairs that must be evaluated and adopts discrete flow matching to significantly decrease the number of denoising iterations. We empirically demonstrate that our approach more effectively captures graph distributions while substantially reducing generation time. |
| title | Hierarchical Discrete Flow Matching for Graph Generation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2604.00236 |