当前位置: X-MOL 学术Knowl. Based 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.)
Multi-component transfer metric learning for handling unrelated source domain samples
Knowledge-Based Systems ( IF 7.2 ) Pub Date : 2020-06-12 , DOI: 10.1016/j.knosys.2020.106132
Chang’an Yi , Yonghui Xu , Han Yu , Yuguang Yan , Yang Liu

Transfer learning (TL) is a machine learning paradigm designed for the problem where the training and test data are from different domains. Existing TL approaches mostly assume that training data from the source domain are collected from multiple views or devices. However, in practical applications, a sample in a target domain often only corresponds to a specific view or device. Without the ability to mitigate the influence of the many unrelated samples, the performance of existing TL approaches may deteriorate for such learning tasks. This problem will be exacerbated if the intrinsic relationships among the source domain samples are unclear. Currently, there is no mechanism for determining the intrinsic characteristics of samples in order to treat them differently during TL. The source domain samples that are not related to the test data not only incur computational overhead, but may result in negative transfer. We propose the multi-component transfer metric learning (MCTML) method to address this challenging research problem. Unlike previous metric-based transfer learning which are only capable of using one metric to transform all the samples, MCTML automatically extracts distinct components from the source domain and learns one metric for each component. For each component, MCTML learns the importance of that component in terms of its predictive power based on the Mahalanobis distance metrics. The optimized combination of components are then used to predict the test data collaboratively. Extensive experiments on public datasets demonstrates its effectiveness in knowledge transfer under this challenging condition.



中文翻译:

多分量传输度量学习,用于处理无关的源域样本

转移学习(TL)是一种机器学习范例,旨在解决培训和测试数据来自不同领域的问题。现有的TL方法大多假设来自源域的训练数据是从多个视图或设备中收集的。但是,在实际应用中,目标域中的样本通常仅对应于特定的视图或设备。如果没有减轻许多无关样本影响的能力,则现有TL方法的性能可能会因此类学习任务而变差。如果源域样本之间的内在关系不清楚,则会加剧此问题。当前,没有机制可以确定样品的内在特性,以便在TL期间对其进行不同处理。与测试数据不相关的源域样本不仅会产生计算开销,而且可能导致负传输。我们提出了多分量传递度量学习(MCTML)方法来解决这一具有挑战性的研究问题。与以前的基于度量的转移学习不同,后者只能使用一个度量来转换所有样本,而MCTML会自动从源域中提取不同的组件,并为每个组件学习一个度量。对于每个组件,MCTML都会根据马氏距离度量依据其预测能力来了解该组件的重要性。然后,将组件的优化组合用于协同预测测试数据。在公共数据集上进行的大量实验证明了其在这种挑战性条件下的知识转移有效性。

更新日期:2020-06-12
down
wechat
bug