Report
Semi-Equivariant Conditional Normalizing Flows
| العنوان: | Semi-Equivariant Conditional Normalizing Flows |
|---|---|
| المؤلفون: | Rozenberg, Eyal, Freedman, Daniel |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science Physics (Other) Quantitative Biology |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Physics - Biological Physics, Quantitative Biology - Biomolecules |
| الوصف: | We study the problem of learning conditional distributions of the form $p(G | \hat G)$, where $G$ and $\hat G$ are two 3D graphs, using continuous normalizing flows. We derive a semi-equivariance condition on the flow which ensures that conditional invariance to rigid motions holds. We demonstrate the effectiveness of the technique in the molecular setting of receptor-aware ligand generation. Comment: ICLR Physics for Machine Learning (Physics4ML) Workshop 2023. arXiv admin note: substantial text overlap with arXiv:2211.04754 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2304.06779 |
| رقم الانضمام: | edsarx.2304.06779 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |