Transitive Transfer Learning
By Ben Tan, Yangqiu Song, Erheng Zhong, Qiang Yang. 2015
195 citations recorded by the source corpus.
Transfer learning, which leverages knowledge from source domains to enhance learning ability in a target domain, has been proven effective in various applications. One major limitation of transfer learning is that the source and target domains should be directly related. If there is little overlap between the two domains, performing knowledge transfer between these domains will not be effective. Inspired by human transitive inference and learning ability, whereby two seemingly unrelated concepts can be connected by a string of intermediate bridges using auxiliary concepts, in this paper we study a novel learning problem: Transitive Transfer Learning (abbreviated to TTL). TTL is aimed at breaking the large domain distances and transfer knowledge even when the source and target domains share few factors directly. For example, when the source and target domains are documents and images respectively, TTL could use some annotated images as the intermediate domain to bridge them. To solve the TTL problem, we propose a learning framework to mimic the human learning process. The framework is composed of an intermediate domain selection component and a knowledge transfer component. Extensive empirical evidence shows that the framework yields state-of-the-art classification accuracies on several classification data sets.
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, methodology): “e.g. images). While this assumption essentially differentiates the multi-view learning from HDA, we have seen in Section 3.3 that HDA methods often rely on an auxiliary intermediate multi-view domain [104, 106, 103, 101, 107, 109]. Hence, HDA/HTL can strongly benefit from multi-view learning techniqu”
- Distant Domain Transfer Learning (2017, methodology): “…five transfer learning algorithms including Adaptive SVM (ASVM) (Aytar and Zisserman 2011), Geodesic Flow Kernel (GFK) (Gong et al. 2012), Landmark (LAN) (Gong, Grauman, and Sha 2013), Deep Transfer Learning (DTL) (Yosinski et al. 2014), and Transitive Transfer Learning (TTL) (Tan et al. 2015).”
- A Survey on Negative Transfer (2020, methodology): “Particularly, DANN and CDAN resulted in severe NT on both datasets, consistent with the observations in [78], [157].”
- Overcoming Negative Transfer: A Survey (2020, background): “Transitive transfer learning focuses on breaking the large domain distances and transferring knowledge even when the source and target domains share few factors directly through intermediate domains [94].”
- Deep Visual Domain Adaptation: A Survey (2018, methodology): “Thus, we use a series of intermediate bridges to connect two seemingly unrelated domains and then perform one-step DA via this bridge, named multi-step (or transitive) DA [91, 92].”
- Personalizing a Dialogue System With Transfer Reinforcement Learning (2016, unknown): “Transfer learning [21, 14, 19, 20, 23] has been applied to other tasks in dialogue systems.”
- Adaptation Across Extreme Variations using Unlabeled Domain Bridges (2019, background): “Similar to us, the benefit of having intermediate domains to guide transfer learning is shown in [50], but in the context of semi-supervised label propagation that requires labeled data from the target domains.”
- Domain Adaptation for Medical Image Analysis: A Survey (2021, unknown): “In terms of adaptation steps, existing methods can be divided into one-step and multi-step DA [10], [39], [40].”
- A Decade Survey of Transfer Learning (2010–2020) (2020, methodology): “To address this issue, several distant domain TL algorithms [61], [63], [72] were proposed.”