arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2201.08514cs.LGeess.SP
收藏

未标记数据如何提高自训练中的泛化能力?单隐层理论分析

How does unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis

Rensselaer Polytechnic Institute(伦斯勒理工学院);Michigan State University(密歇根州立大学);MIT-IBM Watson AI Lab, IBM Research(麻省理工学院-IBM沃森人工智能实验室(IBM研究院));IBM Research(IBM研究院);University at Buffalo(布法罗大学)

Shuai Zhang, Meng Wang, Sijia Liu, Pin-Yu Chen, Jinjun Xiong

摘要:

自训练是一种半监督学习算法,当标记数据有限时,它利用大量未标记数据来改进学习。尽管在经验上取得了成功,但其理论特征仍然难以捉摸。据我们所知,这项工作建立了已知的迭代自训练范式的第一个理论分析,并证明了未标记数据在训练收敛和泛化能力方面的好处。为了使我们的理论分析可行,我们集中在单隐层神经网络的情况下。然而,迭代自训练的理论理解是不平凡的,即使是浅神经网络。其中一个关键挑战是,现有的神经网络景观分析建立在监督学习不再持有(半监督)自训练范式。我们解决了这一挑战,并证明迭代自训练的收敛速度和泛化精度都线性提高了$1/\sqrt{M}$的顺序,其中$M$是未标记样本的数量。还提供了从浅层神经网络到深层神经网络的实验,以证明我们建立的自训练理论见解的正确性。

英文摘要:

Self-training, a semi-supervised learning algorithm, leverages a large amount of unlabeled data to improve learning when the labeled data are limited. Despite empirical successes, its theoretical characterization remains elusive. To the best of our knowledge, this work establishes the first theoretical analysis for the known iterative self-training paradigm and proves the benefits of unlabeled data in both training convergence and generalization ability. To make our theoretical analysis feasible, we focus on the case of one-hidden-layer neural networks. However, theoretical understanding of iterative self-training is non-trivial even for a shallow neural network. One of the key challenges is that existing neural network landscape analysis built upon supervised learning no longer holds in the (semi-supervised) self-training paradigm. We address this challenge and prove that iterative self-training converges linearly with both convergence rate and generalization accuracy improved in the order of $1/\sqrt{M}$, where $M$ is the number of unlabeled samples. Experiments from shallow neural networks to deep neural networks are also provided to justify the correctness of our established theoretical insights on self-training.

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。

↑