BriefGPT.xyz
Feb, 2020
应用于PU学习的部分最优传输
Partial Gromov-Wasserstein with Applications on Positive-Unlabeled Learning
HTML
PDF
Laetitia Chapel, Mokhtar Z. Alaya, Gilles Gasso
TL;DR
本文就偏沃瑟斯坦问题和Gromov-Wasserstein问题提出了精确算法,并以正负样本不平衡学习和不同领域点云为例证明了它们在相应场景下的有效性。
Abstract
optimal transport
(OT) framework allows defining similarity between probability distributions and provides metrics such as the Wasserstein and
gromov-wasserstein
discrepancies. Classical OT problem seeks a transp
→