arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.14066cs.LG
收藏

图网络中的超越置换等变性

Beyond permutation equivariance in graph networks

GlaxoSmithKline(葛兰素史克)

Emma Slade, Francesco Farina

摘要:

在这篇论文草案中,我们介绍了一种新的架构图网络,这是等价于欧几里德集团在$n$维。该模型被设计为以其一般形式与图网络一起工作,并且可以显示为包括作为特殊情况的特定变体。由于它的等方差特性,我们期望所提出的模型相对于经典图架构具有更高的数据效率,并且本质上具有更好的归纳偏差。我们把对这件事的调查推迟到将来的工作中去做。

英文摘要:

In this draft paper, we introduce a novel architecture for graph networks which is equivariant to the Euclidean group in $n$-dimensions. The model is designed to work with graph networks in their general form and can be shown to include particular variants as special cases. Thanks to its equivariance properties, we expect the proposed model to be more data efficient with respect to classical graph architectures and also intrinsically equipped with a better inductive bias. We defer investigating this matter to future work.

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。

↑