arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.09003cs.LGcs.CGmath.ATstat.ML
收藏

基于持久同调的连通性优化表示学习

Connectivity-Optimized Representation Learning via Persistent Homology

University of Salzburg(萨尔茨堡大学);Microsoft(微软);UNC Chapel Hill(北卡罗来纳大学教堂山分校)

Christoph Hofer, Roland Kwitt, Mandar Dixit, Marc Niethammer

摘要:

我们研究的问题,学习表示与可控的连接属性。这在所施加的结构可以在上游杠杆作用的情况下是有益的。特别是,我们通过一种新型的损失控制自动编码器的潜在空间的连通性,从持久的同源性信息操作。在温和的条件下,这种损失是可微的,我们提出了一个理论分析的损失引起的属性。我们选择一类学习作为我们的上游任务,并证明了强加的结构,使知情的参数选择建模类内分布通过核密度估计。在计算机视觉数据上进行评估,这些一类模型表现出有竞争力的性能,并且在低样本量的情况下,大幅优于其他方法。值得注意的是,我们的研究结果表明,在辅助(未标记)数据上训练的单个自动编码器可以生成到潜在空间的映射,该映射可以在数据集上重复使用以进行单类学习。

英文摘要:

We study the problem of learning representations with controllable connectivity properties. This is beneficial in situations when the imposed structure can be leveraged upstream. In particular, we control the connectivity of an autoencoder's latent space via a novel type of loss, operating on information from persistent homology. Under mild conditions, this loss is differentiable and we present a theoretical analysis of the properties induced by the loss. We choose one-class learning as our upstream task and demonstrate that the imposed structure enables informed parameter selection for modeling the in-class distribution via kernel density estimators. Evaluated on computer vision data, these one-class models exhibit competitive performance and, in a low sample size regime, outperform other methods by a large margin. Notably, our results indicate that a single autoencoder, trained on auxiliary (unlabeled) data, yields a mapping into latent space that can be reused across datasets for one-class learning.

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。

↑