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 2106.13786cs.LG
收藏

图网络中通过等方差的数据效率

Data efficiency in graph networks through equivariance

GSK.ai, GlaxoSmithKline(葛兰素史克GSK.ai)

Francesco Farina, Emma Slade

摘要:

我们介绍了一种新的架构图网络,这是等变的坐标嵌入,保持相邻节点之间的距离的任何变换。特别是,它是等变的欧氏和共形正交群在$n$ -维。由于其等方差特性,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。我们表明,在最少量的数据上学习,我们提出的架构可以完美地概括为合成问题中的不可见数据,而标准模型需要更多的训练数据才能达到相当的性能。

英文摘要:

We introduce a novel architecture for graph networks which is equivariant to any transformation in the coordinate embeddings that preserves the distance between neighbouring nodes. In particular, it is equivariant to the Euclidean and conformal orthogonal groups in $n$-dimensions. Thanks to its equivariance properties, the proposed model is extremely more data efficient with respect to classical graph architectures and also intrinsically equipped with a better inductive bias. We show that, learning on a minimal amount of data, the architecture we propose can perfectly generalise to unseen data in a synthetic problem, while much more training data are required from a standard model to reach comparable performance.

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。

↑