Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.23612 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912426510778368 |
|---|---|
| author | Belkadi, Samuel Hong, Steve Chen, Marian Cretu, Miruna Harris, Charles Lio, Pietro |
| author_facet | Belkadi, Samuel Hong, Steve Chen, Marian Cretu, Miruna Harris, Charles Lio, Pietro |
| contents | Autoregressive models excel in efficiency and plug directly into the transformer ecosystem, delivering robust generalization, predictable scalability, and seamless workflows such as fine-tuning and parallelized training. However, they require an explicit sequence order, which contradicts the unordered nature of graphs. In contrast, diffusion models maintain permutation invariance and enable one-shot generation but require up to thousands of denoising steps and additional features for expressivity, leading to high computational costs. Inspired by recent breakthroughs in image generation, especially the success of visual autoregressive methods, we propose MAG, a novel diffusion-free graph generation framework based on next-scale prediction. By leveraging a hierarchy of latent representations, the model progressively generates scales of the entire graph without the need for explicit node ordering. Experiments on both generic and molecular graph datasets demonstrated the potential of this method, achieving inference speedups of up to three orders of magnitude over state-of-the-art methods, while preserving high-quality generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23612 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Diffusion-Free Graph Generation with Next-Scale Prediction Belkadi, Samuel Hong, Steve Chen, Marian Cretu, Miruna Harris, Charles Lio, Pietro Machine Learning Autoregressive models excel in efficiency and plug directly into the transformer ecosystem, delivering robust generalization, predictable scalability, and seamless workflows such as fine-tuning and parallelized training. However, they require an explicit sequence order, which contradicts the unordered nature of graphs. In contrast, diffusion models maintain permutation invariance and enable one-shot generation but require up to thousands of denoising steps and additional features for expressivity, leading to high computational costs. Inspired by recent breakthroughs in image generation, especially the success of visual autoregressive methods, we propose MAG, a novel diffusion-free graph generation framework based on next-scale prediction. By leveraging a hierarchy of latent representations, the model progressively generates scales of the entire graph without the need for explicit node ordering. Experiments on both generic and molecular graph datasets demonstrated the potential of this method, achieving inference speedups of up to three orders of magnitude over state-of-the-art methods, while preserving high-quality generation. |
| title | Diffusion-Free Graph Generation with Next-Scale Prediction |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.23612 |