GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913134374027264 |
|---|---|
| author | Bresson, Roman Divriotis, Konstantinos Lutzeyer, Johannes F. Evdaimon, Iakovos Vazirgiannis, Michalis |
| author_facet | Bresson, Roman Divriotis, Konstantinos Lutzeyer, Johannes F. Evdaimon, Iakovos Vazirgiannis, Michalis |
| contents | We introduce GraViti, a transformer-based graph-level variational autoencoder that maps entire graphs to compact latent vectors. This design produces a true graph-level latent space that supports smooth interpolation, property-guided search, and other downstream tasks beyond the constraints of node-level embeddings. On molecular benchmarks, GraViti learns to decode valid samples that follow the chemical constraints present in the training data, showing that the model recovers domain rules directly from graph-level representations. We also show that, in domains where a reliable canonical node ordering exists such as molecules or bayesian networks, enforcing permutation invariance can prove detrimental for consistent reconstruction. GraViti achieves state-of-the-art reconstruction accuracy on large datasets, and provides solid generative performance. Its single-step decoding offers a lightweight alternative to more complex generation pipelines while maintaining practical sample quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_16668 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance Bresson, Roman Divriotis, Konstantinos Lutzeyer, Johannes F. Evdaimon, Iakovos Vazirgiannis, Michalis Machine Learning Artificial Intelligence We introduce GraViti, a transformer-based graph-level variational autoencoder that maps entire graphs to compact latent vectors. This design produces a true graph-level latent space that supports smooth interpolation, property-guided search, and other downstream tasks beyond the constraints of node-level embeddings. On molecular benchmarks, GraViti learns to decode valid samples that follow the chemical constraints present in the training data, showing that the model recovers domain rules directly from graph-level representations. We also show that, in domains where a reliable canonical node ordering exists such as molecules or bayesian networks, enforcing permutation invariance can prove detrimental for consistent reconstruction. GraViti achieves state-of-the-art reconstruction accuracy on large datasets, and provides solid generative performance. Its single-step decoding offers a lightweight alternative to more complex generation pipelines while maintaining practical sample quality. |
| title | GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2605.16668 |