Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.16883 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915153347346432 |
|---|---|
| author | Nguyen, Van Khoa Boget, Yoann Lavda, Frantzeska Kalousis, Alexandros |
| author_facet | Nguyen, Van Khoa Boget, Yoann Lavda, Frantzeska Kalousis, Alexandros |
| contents | Learning graph generative models over latent spaces has received less attention compared to models that operate on the original data space and has so far demonstrated lacklustre performance. We present GLAD a latent space graph generative model. Unlike most previous latent space graph generative models, GLAD operates on a discrete latent space that preserves to a significant extent the discrete nature of the graph structures making no unnatural assumptions such as latent space continuity. We learn the prior of our discrete latent space by adapting diffusion bridges to its structure. By operating over an appropriately constructed latent space we avoid relying on decompositions that are often used in models that operate in the original data space. We present experiments on a series of graph benchmark datasets that demonstrates GLAD as the first equivariant latent graph generative method achieves competitive performance with the state of the art baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_16883 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GLAD: Improving Latent Graph Generative Modeling with Simple Quantization Nguyen, Van Khoa Boget, Yoann Lavda, Frantzeska Kalousis, Alexandros Machine Learning Learning graph generative models over latent spaces has received less attention compared to models that operate on the original data space and has so far demonstrated lacklustre performance. We present GLAD a latent space graph generative model. Unlike most previous latent space graph generative models, GLAD operates on a discrete latent space that preserves to a significant extent the discrete nature of the graph structures making no unnatural assumptions such as latent space continuity. We learn the prior of our discrete latent space by adapting diffusion bridges to its structure. By operating over an appropriately constructed latent space we avoid relying on decompositions that are often used in models that operate in the original data space. We present experiments on a series of graph benchmark datasets that demonstrates GLAD as the first equivariant latent graph generative method achieves competitive performance with the state of the art baselines. |
| title | GLAD: Improving Latent Graph Generative Modeling with Simple Quantization |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2403.16883 |