Local structure alignment guided domain adaptation with few source samples
Authors: 
Yuying Cai, Jinfeng Li, Baodi Liu, Weifeng Liu, Kai Zhang, Changsheng XuAuthors Info & Claims
Article No.: 60, Pages 1 - 7
Abstract
Domain adaptation has received lots of attention for its high efficiency in dealing with cross-domain learning tasks. Most existing domain adaptation methods adopt the strategies relying on large amounts of source label information, which limits their applications in the real world where only a few label samples are available. We exploit the local geometric connections to tackle this problem and propose a Local Structure Alignment (LSA) guided domain adaptation method in this paper. LSA leverages the Nyström method to describe the distribution difference from the geometric perspective and then perform the distribution alignment between domains. Specifically, LSA constructs a domain-invariant Hessian matrix to locally connect the data of the two domains through minimizing the Nyström approximation error. And then it integrates the domain-invariant Hessian matrix with the semi-supervised learning and finally builds an adaptive semi-supervised model. Extensive experimental results validate that the proposed LSA outperforms the traditional domain adaptation methods especially when only sparse source label information is available.
References
[1]
Mikhail Belkin, Partha Niyogi, and Vikas Sindhwani. 2006. Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples. Journal of Machine Learning Research 7 (2006), 2399--2434.
[2]
Chih Chung Chang and Chih Jen Lin. 2011. LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2, 3 (2011), 1--27.
[3]
Shuo Chen, Fei Zhou, and Qingmin Liao. 2016. Visual domain adaptation using weighted subspace alignment. In Visual Communications & Image Processing. 1--4.
[4]
Wen-Sheng Chu, Fernando De la Torre, and Jeffrey Cohn. 2016. Selective Transfer Machine for Personalized Facial Expression Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 3 (03 2016), 529--545.
[5]
Debasmit Das and C. S. George Lee. 2018. Graph Matching and Pseudo-Label Guided Deep Unsupervised Domain Adaptation. In Proceedings of the International Conference on Artificial Neural Networks (ICANN) (2018), 342--352.
[6]
Petros Drineas, Michael W. Mahoney, and Nello Cristianini. 2005. On the Nyström Method for Approximating a Gram Matrix for Improved Kernel-Based Learning. Journal of Machine Learning Research 6 (2005), 2153--2175.
[7]
Boqing Gong, Yuan Shi, Fei Sha, and K. Grauman. 2012. Geodesic flow kernel for unsupervised domain adaptation. In 2012 IEEE Conference on Computer Vision and Pattern Recognition. 2066--2073.
[8]
Kwang In Kim, Florian Steinke, and Matthias Hein. 2009. Semi-supervised Regression using Hessian energy with an application to semi-supervised dimensionality reduction. Neural Information Processing Systems (2009), 979--987.
[9]
Jinfeng Li, Weifeng Liu, Yicong Zhou, Dapeng Tao, and Liqiang Nie. 2020. Domain Adaptation with Few Labeled Source Samples by Graph Regularization. Neural Processing Letters 51, 1 (2020), 23--39.
[10]
Jinfeng Li, Weifeng Liu, Yicong Zhou, Jun Yu, and Dapeng Tao. 2020. Learning Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation with Few Labeled Source Samples. arXiv:2008.09359 https://ui.adsabs.harvard.edu/abs/2020arXiv200809359L
[11]
Jingjing Li, Jidong Zhao, and Ke Lu. 2016. Joint feature selection and structure preservation for domain adaptation. International Joint Conference on Artificial Intelligence (2016), 1697--1703.
[12]
Limin Li and Zhenyue Zhang. 2019. Semi-supervised Domain Adaptation by Co-variance Matching. IEEE Transactions on Pattern Analysis & Machine Intelligence 41, 11 (2019), 2724--2739.
[13]
M Li, W Bi, J. T Kwok, and B Lu. 2014. Large-Scale Nyström Kernel Matrix Approximation Using Randomized SVD. IEEE Transactions on Neural Networks & Learning Systems 26, 1 (2014), 152--164.
[14]
Jieyan Liu, Jingjing Li, and Ke Lu. 2017. Coupled Local-Global Adaptation for Multi-Source Transfer Learning. NEUROCOMPUTING 275, JAN.31 (2017), 247--254.
[15]
Weifeng Liu, Dacheng Tao, Jun Cheng, and Yuanyan Tang. 2014. Multiview Hessian discriminative sparse coding for image annotation. Computer Vision & Image Understanding 118, jan. (2014), 50--60.
[16]
M. Long, J. Wang, G. Ding, D. Shen, and Q. Yang. 2014. Transfer Learning with Graph Co-Regularization. IEEE Transactions on Knowledge & Data Engineering 26, 7 (2014), 1805--1818.
[17]
Mingsheng Long, Jianmin Wang, Jiaguang Sun, and Philip S Yu. 2015. Domain Invariant Transfer Kernel Learning. IEEE Transactions on Knowledge & Data Engineering 27, 6 (2015), 1519--1532.
[18]
Sinno Jialin Pan and Qiang Yang. 2009. A survey on transfer learning. IEEE Transactions on knowledge and data engineering 22, 10 (2009), 1345--1359.
[19]
Li Shuang, Song Shiji, Huang Gao, Ding Zhengming, and Wu Cheng. 2018. Domain Invariant and Class Discriminative Feature Learning for Visual Domain Adaptation. IEEE Trans Image Process 27 (2018), 4260--4273.
[20]
Si Si, Dacheng Tao, and K P Chan. 2010. Discriminative Hessian Eigenmaps for face recognition. IEEE International Conference on Acoustics, Speech and Signal Processing (2010), 5586--5589.
[21]
Christopher K I Williams and Matthias Seeger. 2000. Using the Nyström Method to Speed Up Kernel Machines. Neural Information Processing Systems (2000), 682--688.
[22]
Lei Zhang, Jingru Fu, Shanshan Wang, David Zhang, and C. L. Philip Chen. 2019. Guide Subspace Learning for Unsupervised Domain Adaptation. IEEE Transactions on Neural Networks and Learning Systems 99 (2019), 1--15.
[23]
Lei Zhang, Shanshan Wang, Guangbin Huang, Wangmeng Zuo, Jian Yang, and David Zhang. 2019. Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation. IEEE Transactions on Neural Networks 30, 12 (2019), 3759--3773.
[24]
Lei Zhang, Wangmeng Zuo, and David Zhang. 2016. LSDT: Latent Sparse Domain Transfer Learning for Visual Adaptation. IEEE Transactions on Image Processing 25, 3 (2016), 1177--1191.
[25]
Fuzhen Zhuang, Zhiyuan Qi, Keyu Duan, Dongbo Xi, and Qing He. 2020. A Comprehensive Survey on Transfer Learning. Proc. IEEE 99 (2020), 1--34.
Index Terms
- Local structure alignment guided domain adaptation with few source samples
Recommendations
Reducing bias to source samples for unsupervised domain adaptation
AbstractUnsupervised Domain Adaptation (UDA) makes predictions for the target domain data while labels are only available in the source domain. Lots of works in UDA focus on finding a common representation of the two domains via domain alignment, ...
Highlights- A novel method named RBDA is proposed for domain adaptation.
- RBDA focuses on reducing the classifier’s bias to source samples.
- Comprehensive experiments demonstrate the effectiveness of RBDA.
Multi-Source Domain Adaptation via Latent Domain Reconstruction
WWW '23 Companion: Companion Proceedings of the ACM Web Conference 2023Multi-Source Domain Adaptation (MSDA) is widely used in various machine learning scenarios for domain shifts between labeled source domains and unlabeled target domains. Conventional MSDA methods are built on a strong hypothesis that data samples from ...
A Two-Way alignment approach for unsupervised multi-Source domain adaptation
Highlights- We introduce a two-way alignment framework for unsupervised multisource domain adaptation task. We first align the target and multiple source domains on ...
AbstractDomain adaptation aims at transferring knowledge from labeled source domain to unlabeled target domain. Current advances primarily concern single source domain and neglect the setting of multiple source domains. Previous unsupervised ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
March 2021
512 pages
ISBN:9781450383080
DOI:10.1145/3444685
- General Chairs:
- Tat-Seng Chua,
- Jingdong Wang,
- Qi Tian,
- Program Chairs:
- Cathal Gurrin,
- Jia Jia,
- Hanwang Zhang,
- Qianru Sun
Copyright © 2021 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 03 May 2021
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- the National Natural Science Foundation of China
- the Open Project Program of the National Laboratory of Pattern Recognition (NLPR)
- the Major Scientific and Technological Projects of CNPC
Conference
MMAsia '20
Sponsor:
Acceptance Rates
Overall Acceptance Rate 59 of 204 submissions, 29%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 60Total Downloads
- Downloads (Last 12 months)5
- Downloads (Last 6 weeks)2
Reflects downloads up to 13 Nov 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in