Multi-Source Spectral Learning without target-data via Dual Regression Heads and Performance-Driven Domain Adaptive Weighting

Zhibin  Xu; Chuanye  He; Hailin  Chen; Meng  Lei

doi:10.6180/jase.202607_30.034

Multi-Source Spectral Learning without target-data via Dual Regression Heads and Performance-Driven Domain Adaptive Weighting

Computer Science and Information Engineering

Hybrid Self-Attention with Lightweight Gating for Chinese English Neural Machine Translation

Zhibin Xu¹, Chuanye He², Hailin Chen¹, and Meng Lei³This email address is being protected from spambots. You need JavaScript enabled to view it.

¹China Certification & Inspection Group Hebei Co., Ltd., Shijiazhuang 050071, Hebei, China

²School of Software, Dalian University of Technology, Dalian 116620, Liaoning, China

³School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, Jiangsu, China

Received: November 11, 2025
Accepted: November 24, 2025
Publication Date: January 19, 2026

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202607_30.034

Near-Infrared Spectroscopy (NIRS) has become one of the most widely used non-destructive techniques for rapid coal quality assessment due to its efficiency, low cost, and suitability for on-site industrial deployment. However, NIRS data collected under different measurement conditions often exhibit significant spectral distribution shifts, which substantially weaken the cross-domain generalization ability of conventional prediction models. To address this challenge, this paper proposes a multi-source spectral learning method tailored for NIRS-based coal analysis. The method integrates a unified multi-source domain adaptation framework, a dual-regression-head architecture, and a performance-driven dynamic weighting strategy, enabling effective cross-domain learning without requiring target-domain data. Experiments conducted on real coal NIRS datasets demonstrate that the proposed approach consistently outperforms existing baselines across multiple measurement scenarios, highlighting its strong potential for accurate and robust rapid coal quality detection.

Keywords: Coal quality assessment; multi-source domain adaptation; cross-domain generalization; transfer learning

[1] Q. Wang, D. Zhang, Y. Dou, Q. Wang, and Y. Wang, (2025) “Advanced Multi-Parameter Prediction of Coal Quality Using LIBS and Ensemble Machine Learning Techniques" ACS Omega 10(33): 37574–37582.
[2] L. Zou, J. Qiao, X. Yu, X. Chen, and M. Lei, (2023) “Intelligent proximate analysis of coal based on near-infrared spectroscopy and multioutput deep learning" IEEE Trans. Artif. Intell. 5(3): 1398–1410.
[3] J. Li, R. Gao, Y. Zhang, L. Zhang, L. Dong, W. Ma, W. Yin, and S. Jia, (2025) “Research on accurate analysis of coal quality using NIRS-XRF fusion spectroscopy in complex coal type scenarios" Opt. Laser Technol. 181: 111734.
[4] J. Tian, M. Li, X. Zhang, M. Lei, L. Ke, and L. Zou, (2024) “Enhancing Moisture Detection in Coal Gravels: ADeep Learning-Based Adaptive Microwave Spectra Fusion Method" Spectrochim. Acta Part A Mol. Biomol. Spectrosc. 313: 124147.
[5] L. Zou, S. Kou, Z. Xu, Z. Tan, and M. Lei, (2025) “Simultaneous prediction of bauxite quality parameters using TC-U net and near-infrared spectroscopy" Memetic Computing 17(2): 25.
[6] B. Hu and J. Wang, (2022) “A weighted multi-source domain adaptation approach for surface defect detection" IET Image Process. 16(8): 2210–2218.
[7] A. J. Parrott, A. C. McIntyre, M. Holden, G. Colquhoun, Z.-P. Chen, D. Littlejohn, and A. Nor don, (2022) “Calibration model transfer in mid-infrared process analysis with in situ attenuated total reflectance immersion probes" Anal. Methods 14(19): 1889–1896.
[8] A. Gretton, K. M. Borgwardt, M. J. Rasch, B. Schölkopf, and A. Smola, (2012) “A kernel two-sample test" J. Mach. Learn. Res. 13(1): 723–773.
[9] B.SunandK.Saenko. “Deep coral: Correlation alignment for deep domain adaptation”. In: Eur. Conf. Comput. Vis. 2016, 443–450.
[10] M. Hassan Pour Zonoozi, V. Seydi, and M. Deypir, (2025) “An unsupervised adversarial domain adaptation based on variational auto-encoder" Mach. Learn. 114(5): 1–26.
[11] S. Zhao, G. Wang, S. Zhang, Y. Gu, Y. Li, Z. Song, P. Xu, R. Hu, H. Chai, and K. Keutzer. “Multi-source distilling domain adaptation”. In: Proc. AAAI Conf. Artif. Intell. 34. 07. 2020, 12975–12983.
[12] X. Peng, Q. Bai, X. Xia, Z. Huang, K. Saenko, and B. Wang. “Moment matching for multi-source domain adaptation”. In: Proc. IEEE/CVF Int. Conf. Comput. Vis. 2019, 1406–1415.
[13] H. Zhao, S. Zhang, G. Wu, J. M. F. Moura, J. P. Costeira, and G. J. Gordon. “Adversarial multiple source domain adaptation”. In: Adv. Neural Inf. Pro cess. Syst. 31. 2018.
[14] L.Yang,Y.Balaji,S.-N.Lim,andA.Shrivastava.“Curriculum manager for source selection in multi-source domain adaptation”. In: Eur. Conf. Comput. Vis. 2020, 608–624.
[15] L. Zhao, X. Wang, Z. Liu, Z. Wang, and Z. Chen, (2024) “Learnable Graph Guided Deep Multi-view Representation Learning via Information Bottleneck" IEEE Trans. Circuits Syst. Video Technol. 35(4): 3303 3314.
[16] L. Zhao, Q. Xie, Z. Li, S. Wu, and Y. Yang, (2024) “DynamicGraphGuidedProgressivePartial View-Aligned Clustering" IEEE Trans. Neural Netw. Learn. Syst. 36(5): 9370–9382.
[17] S. Ma,L. Zhao, M. Lu, Y. Guo, and B. Xu. Consistency Aware Padding for Incomplete Multi-Modal Alignment Clustering Based on Self-Repellent Greedy Anchor Search. [Preprint]. 2025.
[18] L. Zhao, P. Huang, T. Chen, C. Fu, Q. Hu, and Y. Zhang, (2023) “Multi-sentence complementarily generation for text-to-image synthesis" IEEE Trans. Multimed. 26: 8323–8332.
[19] C. Cortes and M. Mohri. “Domain adaptation in regression”. In: Int. Conf. Algorithmic Learn. Theory. 2011, 308–323.
[20] I. Nejjar, Q. Wang, and O. Fink. “Dare-gram: Unsupervised domain adaptation regression by aligning inverse grammatrices”.In:Proc. IEEE/CVFConf.Com put. Vis. Pattern Recognit. 2023, 11744–11754.
[21] H.-R. Yang, C.-X. Ren, and Y.-W. Luo. “Cod: Learning conditional invariant representation for domain adaptation regression”. In: Eur. Conf. Comput. Vis. 2024, 108–125.
[22] Y. Wu, G. Parmigiani, and B. Ren. Multi-source domain adaptation for regression. [Preprint]. 2023.
[23] Y. Zhang, G. Yan, G. Zhao, S. Ma, Z. Liu, and G. Zhao, (2024) “A Dynamic Domain Adaptation Regression Method for Multiple Working Conditions Based on Continual Learning" Ind. Eng. Chem. Res. 63(40): 17252–17265.
[24] Y. Mansour, M. Mohri, and A. Rostamizadeh. “Domain adaptation with multiple sources”. In: Adv. Neu ral Inf. Process. Syst. 21. 2008.
[25] R. Xu, Z. Chen, W. Zuo, J. Yan, and L. Lin. “Deep cocktail network: Multi-source unsupervised domain adaptation with category shift”. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 2018, 3964–3973.
[26] K. Saito, K. Watanabe, Y. Ushiku, and T. Harada. “Maximum classifier discrepancy for unsupervised domain adaptation”. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 2018, 3723–3732.
[27] Y. Zuo, H. Yao, and C. Xu, (2021) “Attention-based multi-source domain adaptation" IEEE Trans. Image Process. 30: 3793–3803.
[28] Y. Ganin and V. Lempitsky. “Unsupervised domain adaptation by backpropagation”. In: Int. Conf. Mach. Learn. 2015, 1180–1189.
[29] M. Long, Z. Cao, J. Wang, and M. I. Jordan. “Conditional adversarial domain adaptation”. In: Adv. Neural Inf. Process. Syst. 31. 2018.
[30] Z. Pei, Z. Cao, M. Long, and J. Wang. “Multi adversarial domain adaptation”. In: Proc. AAAI Conf. Artif. Intell. 32. 1. 2018.
[31] R. Xu, G. Li, J. Yang, and L. Lin. “Larger norm more transferable: An adaptive feature norm approach for unsupervised domain adaptation”. In: Proc. IEEE/CVF Int. Conf. Comput. Vis. 2019, 1426–1435.
[32] Y.Zhang,T.Liu,M.Long,andM.I.Jordan.“Bridging theory and algorithm for domain adaptation”. In: Int. Conf. Mach. Learn. 2019, 7404–7413.
[33] J. Liang, D. Hu, and J. Feng. “Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation”. In: Int. Conf. Mach. Learn. 2020, 6028–6039.
[34] E. Tzeng, J. Hoffman, K. Saenko, and T. Darrell. “Ad versarial discriminative domain adaptation”. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 2017, 7167 7176.
[35] R. Shu, H. H. Bui, H. Narui, and S. Ermon. A dirt-t approach to unsupervised domain adaptation. [Preprint]. 2018.