A Unified Framework for Metric Transfer Learning

Xu, Yonghui; Pan, Sinno Jialin; Xiong, Hui; Wu, Qingyao; Luo, Ronghua; Min, Huaqing; Song, Hengjie

doi:10.1109/tkde.2017.2669193

Cited by 198 publications

(64 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[10] propose a enhanced TrAdaBoost to handle the problem of interregional sandstone microscopic image classification. [26] propose a metric transfer learning framework to learn instance weights and a distance of two different domains in a parallel framework to make knowledge transfer across domains more effective. [11] introduce an ensemble transfer learning to deep neural network that can utilize instances from source domain.…”

Section: Instances-based Deep Transfer Learningmentioning

confidence: 99%

A Survey on Deep Transfer Learning

Tan

Sun

Kong

et al. 2018

Lecture Notes in Computer Science

2,287

1,245

View full text Add to dashboard Cite

As a new classification platform, deep learning has recently received increasing attention from researchers and has been successfully applied to many domains. In some domains, like bioinformatics and robotics, it is very difficult to construct a large-scale well-annotated dataset due to the expense of data acquisition and costly annotation, which limits its development. Transfer learning relaxes the hypothesis that the training data must be independent and identically distributed (i.i.d.) with the test data, which motivates us to use transfer learning to solve the problem of insufficient training data. This survey focuses on reviewing the current researches of transfer learning by using deep neural network and its applications. We defined deep transfer learning, category and review the recent research works based on the techniques used in deep transfer learning.

show abstract

Section: Instances-based Deep Transfer Learningmentioning

confidence: 99%

A Survey on Deep Transfer Learning

Tan

Sun

Kong

et al. 2018

Lecture Notes in Computer Science

2,287

1,245

View full text Add to dashboard Cite

show abstract

“…The approaches in [4], [5], [41] rely on matching the densities or the second-order statistics of the source and the target domains via copula functions or transformations. A metric adapted to the domain adaptation problem is learnt in [42], [43]. In some works, a classifier is learnt in a joint manner with the mapping [44], [45], or directly in the original data domain based on a self-training principle [46].…”

Section: Related Workmentioning

confidence: 99%

Domain Adaptation on Graphs by Learning Aligned Graph Bases

Pilanci

Vural

2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

A common assumption in semi-supervised learning with graph models is that the class label function varies smoothly on the data graph, resulting in the rather strict prior that the label function has low-frequency content. Meanwhile, in many classification problems, the label function may vary abruptly in certain graph regions, resulting in high-frequency components. Although the semi-supervised estimation of class labels is an ill-posed problem in general, in several applications it is possible to find a source graph on which the label function has similar frequency content to that on the target graph where the actual classification problem is defined. In this paper, we propose a method for domain adaptation on graphs motivated by these observations. Our algorithm is based on learning the spectrum of the label function in a source graph with many labeled nodes, and transferring the information of the spectrum to the target graph with fewer labeled nodes. While the frequency content of the class label function can be identified through the graph Fourier transform, it is not easy to transfer the Fourier coefficients directly between the two graphs, since no one-to-one match exists between the Fourier basis vectors of independently constructed graphs in the domain adaptation setting. We solve this problem by learning a transformation between the Fourier bases of the two graphs that flexibly "aligns" them. The unknown class label function on the target graph is then reconstructed such that its spectrum matches that on the source graph while also ensuring the consistency with the available labels. The proposed method is tested in the classification of image, online product review, and social network data sets. Comparative experiments suggest that the proposed algorithm performs better than recent domain adaptation methods in the literature in most settings.

show abstract

“…Domain Adaptation: There also exists another body of non-deep learning transfer paradigms that were often referred to as domain adaption. This however often include methods that not only assume access domain-specific [24,29,[36][37][38] and/or model-specific knowledge of the domains being adapted [17,20,25,27,28,35,41,43], but are also not applicable to deep learning models [10,39] with arbitrary architecture as addressed in our work.…”

Section: Related Workmentioning

confidence: 99%

CHEER: Rich Model Helps Poor Model via Knowledge Infusion

Xiao

Nghia

Hong

et al. 2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

There is a growing interest in applying deep learning (DL) to healthcare, driven by the availability of data with multiple feature channels in rich-data environments (e.g., intensive care units). However, in many other practical situations, we can only access data with much fewer feature channels in a poor-data environments (e.g., at home), which often results in predictive models with poor performance. How can we boost the performance of models learned from such poor-data environment by leveraging knowledge extracted from existing models trained using rich data in a related environment? To address this question, we develop a knowledge infusion framework named CHEER that can succinctly summarize such rich model into transferable representations, which can be incorporated into the poor model to improve its performance. The infused model is analyzed theoretically and evaluated empirically on several datasets. Our empirical results showed that CHEER outperformed baselines by 5.60% to 46.80% in terms of the macro-F1 score on multiple physiological datasets.

show abstract

A Unified Framework for Metric Transfer Learning

Cited by 198 publications

References 24 publications

A Survey on Deep Transfer Learning

A Survey on Deep Transfer Learning

Domain Adaptation on Graphs by Learning Aligned Graph Bases

CHEER: Rich Model Helps Poor Model via Knowledge Infusion

Contact Info

Product

Resources

About