arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.13419cs.LGstat.ML
收藏

迭代SE(3)-Transformers

Iterative SE(3)-Transformers

University of Oxford(牛津大学);University of Washington(华盛顿大学)

Fabian B. Fuchs, Edward Wagstaff, Justas Dauparas, Ingmar Posner

摘要:

在处理三维数据时,可以通过应用所谓的SE(3)-等变模型来确保旋转和平移对称性。蛋白质结构预测是显示这些对称性的任务的一个突出例子。最近在这一领域的工作已经成功地利用了SE(3)-等变模型,应用了迭代SE(3)-等变注意力机制。受此应用程序的启发,我们实现了SE(3)-Transformer的迭代版本,这是一个用于图形数据的SE(3)-等变基于注意力的模型。我们解决了在迭代方式中应用SE(3)-Transformer时出现的额外复杂性,比较了玩具问题上的迭代和单遍版本,并考虑为什么迭代模型在某些问题设置中可能是有益的。我们将实现的代码提供给社区。

英文摘要:

When manipulating three-dimensional data, it is possible to ensure that rotational and translational symmetries are respected by applying so-called SE(3)-equivariant models. Protein structure prediction is a prominent example of a task which displays these symmetries. Recent work in this area has successfully made use of an SE(3)-equivariant model, applying an iterative SE(3)-equivariant attention mechanism. Motivated by this application, we implement an iterative version of the SE(3)-Transformer, an SE(3)-equivariant attention-based model for graph data. We address the additional complications which arise when applying the SE(3)-Transformer in an iterative fashion, compare the iterative and single-pass versions on a toy problem, and consider why an iterative model may be beneficial in some problem settings. We make the code for our implementation available to the community.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑