GraphSPNs: Sum-Product Networks Benefit From Canonical Orderings
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914915557572608 |
|---|---|
| author | Papež, Milan Rektoris, Martin Šmídl, Václav Pevný, Tomáš |
| author_facet | Papež, Milan Rektoris, Martin Šmídl, Václav Pevný, Tomáš |
| contents | Deep generative models have recently made a remarkable progress in capturing complex probability distributions over graphs. However, they are intractable and thus unable to answer even the most basic probabilistic inference queries without resorting to approximations. Therefore, we propose graph sum-product networks (GraphSPNs), a tractable deep generative model which provides exact and efficient inference over (arbitrary parts of) graphs. We investigate different principles to make SPNs permutation invariant. We demonstrate that GraphSPNs are able to (conditionally) generate novel and chemically valid molecular graphs, being competitive to, and sometimes even better than, existing intractable models. We find out that (Graph)SPNs benefit from ensuring the permutation invariance via canonical ordering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_09451 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GraphSPNs: Sum-Product Networks Benefit From Canonical Orderings Papež, Milan Rektoris, Martin Šmídl, Václav Pevný, Tomáš Machine Learning Artificial Intelligence Deep generative models have recently made a remarkable progress in capturing complex probability distributions over graphs. However, they are intractable and thus unable to answer even the most basic probabilistic inference queries without resorting to approximations. Therefore, we propose graph sum-product networks (GraphSPNs), a tractable deep generative model which provides exact and efficient inference over (arbitrary parts of) graphs. We investigate different principles to make SPNs permutation invariant. We demonstrate that GraphSPNs are able to (conditionally) generate novel and chemically valid molecular graphs, being competitive to, and sometimes even better than, existing intractable models. We find out that (Graph)SPNs benefit from ensuring the permutation invariance via canonical ordering. |
| title | GraphSPNs: Sum-Product Networks Benefit From Canonical Orderings |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2408.09451 |