Understanding GNNs for Boolean Satisfiability through Approximation Algorithms
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910580737048576 |
|---|---|
| author | Hůla, Jan Mojžíšek, David Janota, Mikoláš |
| author_facet | Hůla, Jan Mojžíšek, David Janota, Mikoláš |
| contents | The paper deals with the interpretability of Graph Neural Networks in the context of Boolean Satisfiability. The goal is to demystify the internal workings of these models and provide insightful perspectives into their decision-making processes. This is done by uncovering connections to two approximation algorithms studied in the domain of Boolean Satisfiability: Belief Propagation and Semidefinite Programming Relaxations. Revealing these connections has empowered us to introduce a suite of impactful enhancements. The first significant enhancement is a curriculum training procedure, which incrementally increases the problem complexity in the training set, together with increasing the number of message passing iterations of the Graph Neural Network. We show that the curriculum, together with several other optimizations, reduces the training time by more than an order of magnitude compared to the baseline without the curriculum. Furthermore, we apply decimation and sampling of initial embeddings, which significantly increase the percentage of solved problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_15418 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Understanding GNNs for Boolean Satisfiability through Approximation Algorithms Hůla, Jan Mojžíšek, David Janota, Mikoláš Machine Learning The paper deals with the interpretability of Graph Neural Networks in the context of Boolean Satisfiability. The goal is to demystify the internal workings of these models and provide insightful perspectives into their decision-making processes. This is done by uncovering connections to two approximation algorithms studied in the domain of Boolean Satisfiability: Belief Propagation and Semidefinite Programming Relaxations. Revealing these connections has empowered us to introduce a suite of impactful enhancements. The first significant enhancement is a curriculum training procedure, which incrementally increases the problem complexity in the training set, together with increasing the number of message passing iterations of the Graph Neural Network. We show that the curriculum, together with several other optimizations, reduces the training time by more than an order of magnitude compared to the baseline without the curriculum. Furthermore, we apply decimation and sampling of initial embeddings, which significantly increase the percentage of solved problems. |
| title | Understanding GNNs for Boolean Satisfiability through Approximation Algorithms |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2408.15418 |