The quest for the GRAph Level autoEncoder (GRALE)
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917025464451072 |
|---|---|
| author | Krzakala, Paul Melo, Gabriel Laclau, Charlotte d'Alché-Buc, Florence Flamary, Rémi |
| author_facet | Krzakala, Paul Melo, Gabriel Laclau, Charlotte d'Alché-Buc, Florence Flamary, Rémi |
| contents | Although graph-based learning has attracted a lot of attention, graph representation learning is still a challenging task whose resolution may impact key application fields such as chemistry or biology. To this end, we introduce GRALE, a novel graph autoencoder that encodes and decodes graphs of varying sizes into a shared embedding space. GRALE is trained using an Optimal Transport-inspired loss that compares the original and reconstructed graphs and leverages a differentiable node matching module, which is trained jointly with the encoder and decoder. The proposed attention-based architecture relies on Evoformer, the core component of AlphaFold, which we extend to support both graph encoding and decoding. We show, in numerical experiments on simulated and molecular data, that GRALE enables a highly general form of pre-training, applicable to a wide range of downstream tasks, from classification and regression to more complex tasks such as graph interpolation, editing, matching, and prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_22109 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The quest for the GRAph Level autoEncoder (GRALE) Krzakala, Paul Melo, Gabriel Laclau, Charlotte d'Alché-Buc, Florence Flamary, Rémi Machine Learning Artificial Intelligence Although graph-based learning has attracted a lot of attention, graph representation learning is still a challenging task whose resolution may impact key application fields such as chemistry or biology. To this end, we introduce GRALE, a novel graph autoencoder that encodes and decodes graphs of varying sizes into a shared embedding space. GRALE is trained using an Optimal Transport-inspired loss that compares the original and reconstructed graphs and leverages a differentiable node matching module, which is trained jointly with the encoder and decoder. The proposed attention-based architecture relies on Evoformer, the core component of AlphaFold, which we extend to support both graph encoding and decoding. We show, in numerical experiments on simulated and molecular data, that GRALE enables a highly general form of pre-training, applicable to a wide range of downstream tasks, from classification and regression to more complex tasks such as graph interpolation, editing, matching, and prediction. |
| title | The quest for the GRAph Level autoEncoder (GRALE) |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2505.22109 |