当前位置: X-MOL 学术IEEE Trans. Neural Netw. Learn. Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Subspace Distribution Adaptation Frameworks for Domain Adaptation.
IEEE Transactions on Neural Networks and Learning Systems ( IF 10.2 ) Pub Date : 2020-01-24 , DOI: 10.1109/tnnls.2020.2964790
Sentao Chen , Le Han , Xiaolan Liu , Zongyao He , Xiaowei Yang

Domain adaptation tries to adapt a model trained from a source domain to a different but related target domain. Currently, prevailing methods for domain adaptation rely on either instance reweighting or feature transformation. Unfortunately, instance reweighting has difficulty in estimating the sample weights as the dimension increases, whereas feature transformation sometimes fails to make the transformed source and target distributions similar when the cross-domain discrepancy is large. In order to overcome the shortcomings of both methodologies, in this article, we model the unsupervised domain adaptation problem under the generalized covariate shift assumption and adapt the source distribution to the target distribution in a subspace by applying a distribution adaptation function. Accordingly, we propose two frameworks: Bregman-divergence-embedded structural risk minimization (BSRM) and joint structural risk minimization (JSRM). In the proposed frameworks, the subspace distribution adaptation function and the target prediction model are jointly learned. Under certain instantiations, convex optimization problems are derived from both frameworks. Experimental results on the synthetic and real-world text and image data sets show that the proposed methods outperform the state-of-the-art domain adaptation techniques with statistical significance.

中文翻译:

用于域自适应的子空间分布自适应框架。

领域适应尝试使从源领域训练而来的模型适应不同但相关的目标领域。当前,用于域自适应的流行方法依赖于实例重加权或特征变换。不幸的是,实例重加权难以随着维数的增加而估计样本权重,而当跨域差异较大时,特征变换有时无法使变换后的源分布和目标分布相似。为了克服这两种方法的缺点,在本文中,我们对广义协变量偏移假设下的无监督域自适应问题进行建模,并通过应用分布自适应函数将源分布适应于子空间中的目标分布。因此,我们提出了两个框架:Bregman散度嵌入的结构风险最小化(BSRM)和联合结构风险最小化(JSRM)。在提出的框架中,子空间分布自适应函数和目标预测模型是共同学习的。在某些实例中,凸优化问题是从两个框架派生的。在合成和真实世界的文本和图像数据集上的实验结果表明,所提出的方法优于具有统计意义的最新领域自适应技术。
更新日期:2020-01-24
down
wechat
bug