Discriminative Transfer Learning on Manifold

Fang, Zheng; Zhang, Zhongfei

doi:10.1137/1.9781611972832.60

Cited by 6 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, from the form of the constraint gradients ∇ t g j in (28), and the constraint that the columns of T must have unit norm at a local solution, it is easy to observe that the set of the equality constraint gradients {∇ t g j , j = 1, . .…”

Section: Appendix B Convergence Analysis Of the Sqp Methodsmentioning

confidence: 99%

“…Another domain adaptation solution consists of learning a transformation or a projection that aligns the source and the target data [2], [3], [27], [28], [29], [30], [31]. In fact, the idea of aligning the source and the target domains by mapping them to an intermediate space through a transformation has been at the core of many domain adaptation algorithms, some of which can also be applied to problems where the source and the target samples reside in different ambient spaces [32].…”

Section: Related Workmentioning

confidence: 99%

“…, R 2 . From (28), the Hessian ∇ 2 tt g(t, η) of the second term g(t, η) of the Lagrangian in (25) is obtained as a diagonal matrix with entries given by…”

Section: Optimization Of the Transformation Matrixmentioning

confidence: 99%

See 2 more Smart Citations

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

Section: Appendix B Convergence Analysis Of the Sqp Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Domain Adaptation on Graphs by Learning Aligned Graph Bases

Pilanci

Vural

2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…A quite prevalent approach in the literature is to align the source and the target domains using a transformation or a projection [3,4,5,22,23,24,25,26,27,28]. In the assessment of the accuracy of aligning the two distributions, some widely used metrics are the maximum mean discrepancy [29,30,31,6,32,7]; Wasserstein distance [33]; and distribution divergence measures [34].…”

Section: Related Workmentioning

confidence: 99%

Graph Domain Adaptation with Localized Graph Signal Representations

Pilavci¹,

Güneyi²,

Cengiz³

et al. 2019

Preprint

View full text Add to dashboard Cite

In this paper we propose a domain adaptation algorithm designed for graph domains. Given a source graph with many labeled nodes and a target graph with few or no labeled nodes, we aim to estimate the target labels by making use of the similarity between the characteristics of the variation of the label functions on the two graphs. Our assumption about the source and the target domains is that the local behaviour of the label function, such as its spread and speed of variation on the graph, bears resemblance between the two graphs. We estimate the unknown target labels by solving an optimization problem where the label information is transferred from the source graph to the target graph based on the prior that the projections of the label functions onto localized graph bases be similar between the source and the target graphs. In order to efficiently capture the local variation of the label functions on the graphs, spectral graph wavelets are used as the graph bases. Experimentation on various data sets shows that the proposed method yields quite satisfactory classification accuracy compared to reference domain adaptation methods.

show abstract

“…A classifier is trained on the training data, which is then used to estimate the unknown class labels of the test data. On the other hand, domain adaptation methods consider a setting where the distribution of the test data is different from that of the training data [1][2][3][4]. Given many labeled samples in a source domain and much fewer labeled samples in a target domain, domain adaptation algorithms exploit the information available in both domains in order to improve the performance of classification in the target domain.…”

Section: Introductionmentioning

confidence: 99%

Domain adaptation on graphs by learning graph topologies: theoretical analysisand an algorithm

Vural¹

2019

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Traditional machine learning algorithms assume that the training and test data have the same distribution, while this assumption does not necessarily hold in real applications. Domain adaptation methods take into account the deviations in the data distribution. In this work, we study the problem of domain adaptation on graphs. We consider a source graph and a target graph constructed with samples drawn from data manifolds. We study the problem of estimating the unknown class labels on the target graph using the label information on the source graph and the similarity between the two graphs. We particularly focus on a setting where the target label function is learnt such that its spectrum is similar to that of the source label function. We first propose a theoretical analysis of domain adaptation on graphs and present performance bounds that characterize the target classification error in terms of the properties of the graphs and the data manifolds. We show that the classification performance improves as the topologies of the graphs get more balanced, i.e., as the numbers of neighbors of different graph nodes become more proportionate, and weak edges with small weights are avoided. Our results also suggest that graph edges between too distant data samples should be avoided for good generalization performance. We then propose a graph domain adaptation algorithm inspired by our theoretical findings, which estimates the label functions while learning the source and target graph topologies at the same time. The joint graph learning and label estimation problem is formulated through an objective function relying on our performance bounds, which is minimized with an alternating optimization scheme. Experiments on synthetic and real data sets suggest that the proposed method outperforms baseline approaches.

show abstract

Discriminative Transfer Learning on Manifold

Cited by 6 publications

References 20 publications

Domain Adaptation on Graphs by Learning Aligned Graph Bases

Domain Adaptation on Graphs by Learning Aligned Graph Bases

Graph Domain Adaptation with Localized Graph Signal Representations

Domain adaptation on graphs by learning graph topologies: theoretical analysisand an algorithm

Contact Info

Product

Resources

About