A survey on heterogeneous transfer learning
By Oscar Day, Taghi M. Khoshgoftaar. 2017
362 citations recorded by the source corpus.
Transfer learning has been demonstrated to be effective for many real-world applications as it exploits knowledge present in labeled training data from a source domain to enhance a model’s performance in a target domain, which has little or no labeled target training data. Utilizing a labeled source, or auxiliary, domain for aiding a target task can greatly reduce the cost and effort of collecting sufficient training labels to create an effective model in the new target distribution. Currently, most transfer learning methods assume the source and target domains consist of the same feature spaces which greatly limits their applications. This is because it may be difficult to collect auxiliary labeled source domain data that shares the same feature space as the target domain. Recently, heterogeneous transfer learning methods have been developed to address such limitations. This, in effect, expands the application of transfer learning to many other real-world tasks such as cross-language text categorization, text-to-image classification, and many others. Heterogeneous transfer learning is characterized by the source and target domains having differing feature spaces, but may also be combined with other issues such as differing data distributions and label spaces. These can present significant challenges, as one must develop a method to bridge the feature spaces, data distributions, and other gaps which may be present in these cross-domain learning tasks. This paper contributes a comprehensive survey and analysis of current methods designed for performing heterogeneous transfer learning tasks to provide an updated, centralized outlook into current methodologies.
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
- A Survey on Data Collection for Machine Learning: A Big Data - AI Integration Perspective (2018, background): “More recent surveys [173], [178] classify most of the traditional transfer learning techniques as homogeneous transfer learning where the feature spaces of the source and target tasks are the same.”
- A Comprehensive Survey on Transfer Learning (2019, background): “[4] K. Weiss, T. M. Khoshgoftaar, and D. Wang, “A survey of transfer learning,” J. Big Data, vol. 3, no. 1, Dec. 2016.”
- Deep Learning for Sensor-based Human Activity Recognition (2020, background): “We can also categorize the discrepancy into homogeneous discrepancy and heterogeneous discrepancy by character [36].”
- Hyperspectral Image Classification—Traditional to Deep Models: A Survey for Future Prospects (2021, background): “the knowledge between them is known as heterogeneous transfer learning (a detailed survey of such methods can be found in [228]).”
- Demystifying IoT Security: An Exhaustive Survey on IoT Vulnerabilities and a First Empirical Look on Internet-Scale IoT Exploitations (2019, neutral): “Applying transfer learning algorithms [215] to the currently available knowledge related to IoT vulnerabilities could ameliorate and automate the tasks of vulnerability assessment and simulation in order to extrapolate this knowledge to various IoT devices, platforms and realms.”
- A Decade Survey of Transfer Learning (2010–2020) (2020, neutral): “Moreover, heterogeneous TL is speciallydiscussedbythesurvey[6].”
- A Survey of Zero-Shot Learning (2019, methodology): “According to [23, 114], based on whether the feature spaces and label spaces in the source and target domains/tasks are the same, transfer learning can be classified into homogeneous transfer learning and heterogeneous transfer learning .”