Hybrid Heterogeneous Transfer Learning through Deep Learning

By Joey Tianyi Zhou, Sinno Jialin Pan, Ivor Wai-Hung Tsang, Yan Yan. 2014

181 citations recorded by the source corpus.

Most previous heterogeneous transfer learning methods learn a cross-domain feature mapping between heterogeneous feature spaces based on a few cross-domain instance-correspondences, and these corresponding instances are assumed to be representative in the source and target domains respectively. However, in many real-world scenarios, this assumption may not hold. As a result, the constructed feature mapping may not be precisely due to the bias issue of the correspondences in the target or (and) source domain(s). In this case, a classifier trained on the labeled transformed-source-domain data may not be useful for the target domain. In this paper, we present a new transfer learning framework called Hybrid Heterogeneous Transfer Learning (HHTL), which allows the corresponding instances across domains to be biased in either the source or target domain. Specifically, we propose a deep learning approach to learn a feature mapping between cross-domain heterogeneous features as well as a better feature representation for mapped data to reduce the bias issue caused by the cross-domain correspondences. Extensive experiments on several multilingual sentiment classification tasks verify the effectiveness of our proposed approach compared with some baseline methods.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, background): “, multilingual text Domain Adaptation for Visual Applications: A Comprehensive Survey 3 Fig. 2 An overview of different transfer learning approaches. (Image: Courtesy to S.J. Pan [37].) classiﬁcation [9, 10, 11], sentiment analysis [12, 13], WiFi-based localization [14], speech recognition across di”
Transfer Hashing with Privileged Information (2016, background): “…knowledge across different domains so that rich source domain knowlege can be used to build better classifiers on a target domain where the transferred knowledge can be labels [Zhou et al., 2014b], features [Pan et al., 2011], crossdomain correspondences [Zhou et al., 2014a; Zhou et al., 2016].”
Multimodal Transfer Deep Learning with Applications in Audio-Visual Recognition (2014, methodology): “In this regard, several approaches such as DCCA ([6]), DeViSE ([7]), HHTL ([8]), and DCCAE ([9]) have proposed to utilize deep neural networks to obtain abstract representation of data (e.”
Deep Asymmetric Transfer Network for Unbalanced Domain Adaptation (2018, background): “Therefore, some recent works start to apply deep neural networks to bridge the source and target domains to perform domain adaptation (Zhuang et al. 2015; Shu et al. 2015; Hubert Tsai, Yeh, and Frank Wang 2016; Zhou et al. 2014).”
Bi-Transferring Deep Neural Networks for Domain Adaptation (2016, background): “Deep learning techniques have also been proposed to heterogeneous transfer learning (Socher et al., 2013; Zhou et al., 2014; Kan et al., 2015; Long et al., 2015), where knowledge is transferred from one modality to another based on the correspondences at hand.”