{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:26:28Z","timestamp":1771611988298,"version":"3.50.1"},"reference-count":46,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T00:00:00Z","timestamp":1744588800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>This paper presents a novel unsupervised domain adaptation (UDA) framework that integrates information-theoretic principles to mitigate distributional discrepancies between source and target domains. The proposed method incorporates two key components: (1) relative entropy regularization, which leverages Kullback\u2013Leibler (KL) divergence to align the predicted label distribution of the target domain with a reference distribution derived from the source domain, thereby reducing prediction uncertainty; and (2) measure propagation, a technique that transfers probability mass from the source domain to generate pseudo-measures\u2014estimated probabilistic representations\u2014for the unlabeled target domain. This dual mechanism enhances both global feature alignment and semantic consistency across domains. Extensive experiments on benchmark datasets (OfficeHome and DomainNet) demonstrate that the proposed approach consistently outperforms State-of-the-Art methods, particularly in scenarios with significant domain shifts. These results confirm the robustness, scalability, and theoretical grounding of our framework, offering a new perspective on the fusion of information theory and domain adaptation.<\/jats:p>","DOI":"10.3390\/e27040426","type":"journal-article","created":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T03:59:06Z","timestamp":1744689546000},"page":"426","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Unsupervised Domain Adaptation Method Based on Relative Entropy Regularization and Measure Propagation"],"prefix":"10.3390","volume":"27","author":[{"given":"Lianghao","family":"Tan","sequence":"first","affiliation":[{"name":"Department of Computer Science, Arizona State University, Tempe, AZ 85281, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5201-0792","authenticated-orcid":false,"given":"Zhuo","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Arizona State University, Tempe, AZ 85281, USA"}]},{"given":"Yongjia","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Language Science, University of California, Irvine, CA 92697, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2586-2389","authenticated-orcid":false,"given":"Xiaoyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Arizona State University, Tempe, AZ 85281, USA"}]},{"given":"Huangqi","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Georgia Institute of Technology, Atlanta, GA 30332, USA"}]},{"given":"Shubing","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, North Carolina at Chapel Hill, Orange, GA 27599, USA"}]},{"given":"Weixi","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, New York University, Brooklyn, NY 10003, USA"}]},{"given":"Zhiyuan","family":"Xiang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of California, San Diego, CA 92093, USA"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e25","DOI":"10.1561\/116.00000192","article-title":"Deep unsupervised domain adaptation: A review of recent advances and perspectives","volume":"11","author":"Liu","year":"2022","journal-title":"APSIPA Trans. Signal Inf. Process."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Park, G.Y., and Lee, S.W. (2021, January 11\u201317). Information-theoretic regularization for multi-source domain adaptation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00908"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2407","DOI":"10.1109\/TMM.2021.3080516","article-title":"Informative feature disentanglement for unsupervised domain adaptation","volume":"24","author":"Deng","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ahmed, S.M., Raychaudhuri, D.S., Paul, S., Oymak, S., and Roy-Chowdhury, A.K. (2021, January 20\u201325). Unsupervised multi-source domain adaptation without access to source data. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00997"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2502","DOI":"10.1109\/TMM.2021.3082687","article-title":"Uncertainty-aware unsupervised domain adaptation in object detection","volume":"24","author":"Guan","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1109\/TPAMI.2022.3146234","article-title":"Semi-supervised heterogeneous domain adaptation: Theory and algorithms","volume":"45","author":"Fang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"6263","DOI":"10.1109\/TNNLS.2021.3073119","article-title":"Adversarial entropy optimization for unsupervised domain adaptation","volume":"33","author":"Ma","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Shi, Y., Ying, X., and Yang, J. (2022). Deep unsupervised domain adaptation with time series sensor data: A survey. Sensors, 22.","DOI":"10.3390\/s22155507"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"4018","DOI":"10.1109\/TPAMI.2022.3217046","article-title":"Unsupervised domain adaptation of object detectors: A survey","volume":"46","author":"Oza","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_10","unstructured":"Xu, T., Chen, W., Wang, P., Wang, F., Li, H., and Jin, R. (2021). Cdtrans: Cross-domain transformer for unsupervised domain adaptation. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Mirza, M.J., Micorek, J., Possegger, H., and Bischof, H. (2022, January 18\u201324). The norm must go on: Dynamic unsupervised domain adaptation by normalization. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01435"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Huang, J., Guan, D., Xiao, A., Lu, S., and Shao, L. (2022, January 18\u201324). Category contrast for unsupervised domain adaptation in visual tasks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00127"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/MBITS.2022.3212978","article-title":"Role of deep learning in wireless communications","volume":"2","author":"Yu","year":"2022","journal-title":"IEEE BITS Inf. Theory Mag."},{"key":"ref_14","first-page":"9","article-title":"Shannon entropy in artificial intelligence and its applications based on information theory","volume":"13","author":"Ali","year":"2023","journal-title":"J. Appl. Emerg. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1007\/s10796-022-10327-9","article-title":"A theory-based deep-learning approach to detecting disinformation in financial social media","volume":"25","author":"Chung","year":"2023","journal-title":"Inf. Syst. Front."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1007\/s10664-022-10147-0","article-title":"Defect prediction using deep learning with Network Portrait Divergence for software evolution","volume":"27","author":"Walunj","year":"2022","journal-title":"Empir. Softw. Eng."},{"key":"ref_17","unstructured":"Cui, S., Wang, S., Zhuo, J., Li, L., Huang, Q., and Tian, Q. (2021). Fast batch nuclear-norm maximization and minimization for robust domain adaptation. arXiv."},{"key":"ref_18","unstructured":"Hamidi, S.M. (2024). The Interplay of Information Theory and Deep Learning: Frameworks to Improve Deep Learning Efficiency and Accuracy, University of Waterloo."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Shwartz Ziv, R., and LeCun, Y. (2024). To compress or not to compress\u2014Self-supervised learning and information theory: A review. Entropy, 26.","DOI":"10.3390\/e26030252"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"963","DOI":"10.1007\/s13042-021-01429-y","article-title":"Robust semi-supervised spatial picture fuzzy clustering with local membership and KL-divergence for image segmentation","volume":"13","author":"Wu","year":"2022","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_21","unstructured":"Sanokowski, S., Hochreiter, S., and Lehner, S. (2024). A diffusion model framework for unsupervised neural combinatorial optimization. arXiv."},{"key":"ref_22","unstructured":"Lee, K.S., Tran, N.T., and Cheung, N.M. (, January 3\u20138). Infomax-gan: Improved adversarial image generation via information maximization and contrastive learning. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Li, J., Ren, Y., and Deng, K. (2022, January 25\u201329). FairGAN: GANs-based fairness-aware learning for recommendations with implicit feedback. Proceedings of the ACM Web Conference 2022, Lyon, France.","DOI":"10.1145\/3485447.3511958"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"109088","DOI":"10.1016\/j.patcog.2022.109088","article-title":"Unsupervised domain adaptation via deep conditional adaptation network","volume":"134","author":"Ge","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, Z., and He, W. (2023, January 17\u201324). Class relationship embedded learning for source-free unsupervised domain adaptation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00736"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Saito, K., Watanabe, K., Ushiku, Y., and Harada, T. (2018, January 18\u201323). Maximum classifier discrepancy for unsupervised domain adaptation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00392"},{"key":"ref_28","unstructured":"Long, M., Cao, Z., Wang, J., and Jordan, M.I. (2018). Conditional adversarial domain adaptation. Adv. Neural Inf. Process. Syst., 31."},{"key":"ref_29","first-page":"3521","article-title":"Adversarial-learned loss for domain adaptation","volume":"34","author":"Chen","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Hung, C.C., Lange, L., and Str\u00f6tgen, J. (2023). TADA: Efficient task-agnostic domain adaptation for transformers. arXiv.","DOI":"10.18653\/v1\/2023.findings-acl.31"},{"key":"ref_31","unstructured":"Zhang, Y., Liu, T., Long, M., and Jordan, M. (2019, January 10\u201315). Bridging theory and algorithm for domain adaptation. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Hu, L., Kan, M., Shan, S., and Chen, X. (2020, January 13\u201319). Unsupervised domain adaptation with hierarchical gradient synchronization. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00410"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Cui, S., Wang, S., Zhuo, J., Su, C., Huang, Q., and Tian, Q. (2020, January 13\u201319). Gradually vanishing bridge for adversarial domain adaptation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01247"},{"key":"ref_34","first-page":"11079","article-title":"How does the combined risk affect the performance of unsupervised domain adaptation approaches?","volume":"35","author":"Zhong","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_35","unstructured":"Cui, S., Jin, X., Wang, S., He, Y., and Huang, Q. (2020). Heuristic Domain Adaptation, NeurlPS."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wei, G., Lan, C., Zeng, W., and Chen, Z. (2021, January 20\u201325). Metaalign: Coordinating domain alignment and classification for unsupervised domain adaptation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01637"},{"key":"ref_37","first-page":"13834","article-title":"Toalign: Task-oriented alignment for unsupervised domain adaptation","volume":"34","author":"Wei","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1016\/j.neunet.2023.02.006","article-title":"Data augmentation with norm-AE and selective pseudo-labelling for unsupervised domain adaptation","volume":"161","author":"Wang","year":"2023","journal-title":"Neural Netw."},{"key":"ref_39","first-page":"1","article-title":"A contrastive deep learning approach to cryptocurrency portfolio with us treasuries","volume":"1","author":"Li","year":"2024","journal-title":"J. Comput. Technol. Appl. Math."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Chang, W.G., You, T., Seo, S., Kwak, S., and Han, B. (2019, January 15\u201320). Domain-specific batch normalization for unsupervised domain adaptation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00753"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"7842","DOI":"10.1109\/TIP.2021.3109530","article-title":"Joint clustering and discriminative feature alignment for unsupervised domain adaptation","volume":"30","author":"Deng","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_42","unstructured":"Lee, S., Kim, D., Kim, N., and Jeong, S.G. (November, January 27). Drop to adapt: Learning discriminative features for unsupervised domain adaptation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republc of Korea."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Cao, Z., Ma, L., Long, M., and Wang, J. (2018, January 8\u201314). Partial adversarial domain adaptation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01237-3_9"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Zhang, L., Xu, L., Motamed, S., Chakraborty, S., and De la Torre, F. (2024, January 1\u20136). D3GU: Multi-target Active Domain Adaptation via Enhancing Domain Alignment. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.","DOI":"10.1109\/WACV57701.2024.00256"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"106749","DOI":"10.1016\/j.neunet.2024.106749","article-title":"DCST: Dual Cross-Supervision for Transformer-based Unsupervised Domain Adaptation","volume":"181","author":"Cheng","year":"2025","journal-title":"Neural Netw."},{"key":"ref_46","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/4\/426\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:14:26Z","timestamp":1760030066000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/4\/426"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,14]]},"references-count":46,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["e27040426"],"URL":"https:\/\/doi.org\/10.3390\/e27040426","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,14]]}}}