arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.05419cs.LG
收藏

界面拉普拉斯学习:可学习的界面项助力半监督学习

Interface Laplace Learning: Learnable Interface Term Helps Semi-Supervised Learning

Tsinghua University(清华大学)

Tangjun Wang, Chenglong Bao, Zuoqiang Shi

AI总结:

本文提出界面拉普拉斯学习框架,通过在类别界面处引入可学习界面项,突破函数全局光滑假设,并在极低标记率下取得优于现有半监督方法的性能。

摘要:

我们提出了一种新的框架,称为界面拉普拉斯学习(Interface Laplace learning),用于基于图的半监督学习。受不同类别之间应存在函数值非光滑的界面这一观察的启发,我们引入了一个包含界面项的拉普拉斯学习模型。该模型挑战了长期以来认为函数在所有未标记点处都光滑的假设。在所提出的方法中,我们在界面位置向拉普拉斯学习模型添加了一个界面项。我们提供了一个实用算法,利用k跳邻域索引来近似界面位置,并从标记数据中学习界面项,而无需人工设计。我们的方法高效且有效,并且我们给出了大量实验,表明在MNIST、FashionMNIST和CIFAR-10数据集上,在极低标记率下,界面拉普拉斯学习取得了比其他近期半监督学习方法更好的性能。

英文摘要:

We introduce a novel framework, called Interface Laplace learning, for graph-based semi-supervised learning. Motivated by the observation that an interface should exist between different classes where the function value is non-smooth, we introduce a Laplace learning model that incorporates an interface term. This model challenges the long-standing assumption that functions are smooth at all unlabeled points. In the proposed approach, we add an interface term to the Laplace learning model at the interface positions. We provide a practical algorithm to approximate the interface positions using k-hop neighborhood indices, and to learn the interface term from labeled data without artificial design. Our method is efficient and effective, and we present extensive experiments demonstrating that Interface Laplace learning achieves better performance than other recent semi-supervised learning approaches at extremely low label rates on the MNIST, FashionMNIST, and CIFAR-10 datasets.

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。

↑