Abstract
Domain adaptation aims to generalize a model from a source domain to tackle tasks in a related but different target domain. Traditional domain adaptation algorithms assume that enough labeled data, which are treated as the prior knowledge are available in the source domain. However, these algorithms will be infeasible when only a few labeled data exist in the source domain, thus the performance decreases significantly. To address this challenge, we propose a Domain-invariant Graph Learning (DGL) approach for domain adaptation with only a few labeled source samples. Firstly, DGL introduces the Nyström method to construct a plastic graph that shares similar geometric property with the target domain. Then, DGL flexibly employs the Nyström approximation error to measure the divergence between the plastic graph and source graph to formalize the distribution mismatch from the geometric perspective. Through minimizing the approximation error, DGL learns a domain-invariant geometric graph to bridge the source and target domains. Finally, we integrate the learned domain-invariant graph with the semi-supervised learning and further propose an adaptive semi-supervised model to handle the cross-domain problems. The results of extensive experiments on popular datasets verify the superiority of DGL, especially when only a few labeled source samples are available.
- [1] . 2011. Interior-point Methods for Large-scale Cone Programming.Google Scholar
- [2] . 2006. Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. Journal of Machine Learning Research 7 (2006), 2399–2434.Google Scholar
Digital Library
- [3] . 2016. Visual domain adaptation using weighted subspace alignment. In Proceedings of the Visual Communications and Image Processing (VCIP).Google Scholar
Cross Ref
- [4] . 2017. Selective transfer machine for personalized facial expression analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 3 (2017), 529–545.Google Scholar
Digital Library
- [5] . 2015. Optimal transport for domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 9 (2015).Google Scholar
Digital Library
- [6] . 2007. Boosting for transfer learning. In Proceedings of the International Conference on Machine Learning (ICML). 193–200.Google Scholar
Digital Library
- [7] . 2018. Graph matching and pseudo-label guided deep unsupervised domain adaptation. In Proceedings of the International Conference on Artificial Neural Networks (ICANN). 342–352.Google Scholar
Cross Ref
- [8] . 2017. Robust transfer metric learning for image classification. IEEE Transactions on Image Processing 26, 2 (2017), 660–670.Google Scholar
Digital Library
- [9] . 2005. On the Nystr\( \ddot{o} \)m method for approximating a Gram matrix for improved kernel-based learning. Journal of Machine Learning Research 6 (2005), 2153–2175.Google Scholar
Digital Library
- [10] . 2004. Spectral grouping using the Nyström method. IEEE Transactions on Pattern Analysis and Machine Intelligence 26, 2 (2004), 214–225.Google Scholar
Digital Library
- [11] . 2008. Knowledge transfer via multiple model local structure mapping. In The ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 283–291.Google Scholar
Digital Library
- [12] . 2012. Geodesic flow kernel for unsupervised domain adaptation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2066–2073.Google Scholar
- [13] . 2006. A kernel method for the two-sample-problem. In Proceedings of the Advances in Neural Information Processing Systems (NIPS). 513–520.Google Scholar
- [14] 2007. Caltech-256 object category dataset. CalTech Report (2007).Google Scholar
- [15] . 2020. Cross-domain sentiment encoding through stochastic word embedding. IEEE Transactions on Knowledge and Data Engineering 32, 10 (2020), 1909–1922.Google Scholar
Cross Ref
- [16] . 2020. Resource efficient domain adaptation. In Proceedings of the 28th ACM International Conference on Multimedia. 2220–2228.Google Scholar
Digital Library
- [17] . 2020. Adaptively-accumulated knowledge transfer for partial domain adaptation. In Proceedings of the ACM International Conference on Multimedia. 1606–1614.Google Scholar
Digital Library
- [18] . 2015. Large-Scale Nystr\( \ddot{o} \)m Kernel Matrix Approximation Using Randomized SVD. IEEE Transactions on Neural Networks and Learning System 26, 1 (2015), 152–164.Google Scholar
Cross Ref
- [19] . 2017. Knowledge-based document embedding for cross-domain text classification. In Proceedings of the International Joint Conference on Neural Networks (IJCNN). 1395–1402.Google Scholar
Cross Ref
- [20] . 2011. Libsvm: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2, 3 (2011), 1–27.Google Scholar
Digital Library
- [21] . 2019. Structure-preserved unsupervised domain adaptation. IEEE Transactions on Knowledge and Data Engineering 31, 4 (2019), 799–812.Google Scholar
Digital Library
- [22] . 2019. Adaptive transfer network for cross-domain person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7202–7211.Google Scholar
Cross Ref
- [23] . 2014. Adaptation regularization: A general framework for transfer learning. IEEE Transactions on Knowledge and Data Engineering 26, 5 (2014), 1076–1089.Google Scholar
Digital Library
- [24] . 2014. Transfer joint matching for unsupervised domain adaptation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1410–1417.Google Scholar
Digital Library
- [25] . 2015. Domain invariant transfer kernel learning. IEEE Transactions on Knowledge and Data Engineering 27, 6 (2015), 1519–1532.Google Scholar
Digital Library
- [26] . 2011. Domain adaptation via transfer component analysis. IEEE Transactions on Neural Networks 22, 2 (2011), 199–210.Google Scholar
Digital Library
- [27] . 2010. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering 22, 10 (2010), 1345–1359.Google Scholar
Digital Library
- [28] . 2020. Domain adaptation on graphs by learning aligned graph bases. IEEE Transactions on Knowledge and Data Engineering (2020).Google Scholar
- [29] . 2011. Dyadic transfer learning for cross-domain image classification. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). 551–556.Google Scholar
Digital Library
- [30] . 2017. Balanced distribution adaptation for transfer learning. In Proceedings of the IEEE International Conference on Data Mining (ICDM). 1129–1134.Google Scholar
Cross Ref
- [31] . 2018. Visual domain adaptation with manifold embedded distribution alignment. In Proceedings of the ACM International Conference on Multimedia (ACMMM).Google Scholar
Digital Library
- [32] . 2019. A general domain specific feature transfer framework for hybrid domain adaptation. IEEE Transactions on Knowledge and Data Engineering 31, 8 (2019), 1440–1451.Google Scholar
Digital Library
- [33] . 2000. Using the Nystr\( \ddot{o} \)m Method to speed up kernel machines. In Proceedings of Advances in Neural Information Processing Systems (NIPS). 682–688.Google Scholar
- [34] . 2014. Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence 36, 6 (2014), 1134–1148.Google Scholar
Digital Library
- [35] . 2018. Learning domain-invariant subspace using domain features and independence maximization. IEEE Transactions on Cybernetics 48, 1 (2018), 288–299.Google Scholar
Cross Ref
- [36] . 2015. Boosted multifeature learning for cross-domain transfer. ACM Transactions on Multimedia Computing, Communications, and Applications 11, 3 (2015).Google Scholar
Digital Library
- [37] . 2015. Semi-supervised domain adaptation with subspace learning for visual recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2142–2150.Google Scholar
Cross Ref
- [38] . 2014. Exploiting click constraints and multi-view features for image re-ranking. IEEE Transactions on Multimedia 16, 1 (2014), 159–168.Google Scholar
Cross Ref
- [39] . 2014. Click prediction for web image reranking using multimodal sparse coding. IEEE Transactions on Image Processing 23, 5 (2014), 2019–2032.Google Scholar
Cross Ref
- [40] . 2017. Joint geometrical and statistical alignment for visual domain adaptation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5150–5158.Google Scholar
Cross Ref
- [41] . 2008. Improved Nystr\( \ddot{o} \)m Low-Rank Approximation and Error Analysis. In Proceedings of the International Conference on Machine Learning (ICML). 1232–1239.Google Scholar
Digital Library
- [42] . 2019. Transfer adaptation learning: A decade survey. Corr abs/1903.04687 (2019).
arxiv:1903.04687 http://arxiv.org/abs/1903.04687Google Scholar - [43] . 2019. Guide subspace learning for unsupervised domain adaptation. IEEE Transactions on Neural Networks and Learning Systems (2019), 1–15.Google Scholar
- [44] . 2018. Structural domain adaptation with latent graph alignment. In Proceedings of the IEEE International Conference on Image Processing (ICIP). 3753–3757.Google Scholar
Cross Ref
- [45] . 2012. Mining distinction and commonality across multiple domains using generative model for text classification. IEEE Transactions on Knowledge and Data Engineering 24, 11 (2012), 2025–2039.Google Scholar
Digital Library
Index Terms
Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation
Recommendations
Semi-supervised adversarial discriminative domain adaptation
AbstractDomain adaptation is a potential method to train a powerful deep neural network across various datasets. More precisely, domain adaptation methods train the model on training data and test that model on a completely separate dataset. The ...
Domain Adaptation for Face Recognition: Targetize Source Domain Bridged by Common Subspace
In many applications, a face recognition model learned on a source domain but applied to a novel target domain degenerates even significantly due to the mismatch between the two domains. Aiming at learning a better face recognition model for the target ...
Graph Adaptive Knowledge Transfer for Unsupervised Domain Adaptation
Computer Vision – ECCV 2018AbstractUnsupervised domain adaptation has caught appealing attentions as it facilitates the unlabeled target learning by borrowing existing well-established source domain knowledge. Recent practice on domain adaptation manages to extract effective ...






Comments