arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.07546math.FAcs.LG
收藏

置换不变表示及其在图深度学习中的应用

Permutation Invariant Representations with Applications to Graph Deep Learning

University of Maryland, College Park(马里兰大学帕克分校);Verisk Analytics(韦里斯克分析公司)

Radu Balan, Naveed Haghani, Maneesh Singh

摘要:

本文主要给出了由模任意行置换确定的矩阵生成的商空间的两种欧氏嵌入。最初的应用是在图的深度学习中,其中学习任务对节点重新标记是不变的。介绍了两种基于排序和基于多元多项式代数的嵌入方案。虽然这两种嵌入表现出计算复杂性指数的问题大小,排序为基础的嵌入是全球bi-Lipschitz,并承认一个低维的目标空间。另外,可以以最小冗余和低计算成本实现几乎处处单射方案。反过来,这证明了几乎任何分类器都可以以任意小的性能损失来实现。数值实验进行了两个数据集,化合物数据集(QM 9)和蛋白质数据集(蛋白质)。

英文摘要:

This paper presents primarily two Euclidean embeddings of the quotient space generated by matrices that are identified modulo arbitrary row permutations. The original application is in deep learning on graphs where the learning task is invariant to node relabeling. Two embedding schemes are introduced, one based on sorting and the other based on algebras of multivariate polynomials. While both embeddings exhibit a computational complexity exponential in problem size, the sorting based embedding is globally bi-Lipschitz and admits a low dimensional target space. Additionally, an almost everywhere injective scheme can be implemented with minimal redundancy and low computational cost. In turn, this proves that almost any classifier can be implemented with an arbitrary small loss of performance. Numerical experiments are carried out on two data sets, a chemical compound data set (QM9) and a proteins data set (PROTEINS).

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。

↑