{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T18:15:47Z","timestamp":1780078547583,"version":"3.54.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100006708","name":"Bauhaus-Universit\u00e4t Weimar","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006708","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Engineering with Computers"],"published-print":{"date-parts":[[2022,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In machine learning, if the training data is independently and identically distributed as the test data then a trained model can make an accurate predictions for new samples of data. Conventional machine learning has a strong dependence on massive amounts of training data which are domain specific to understand their latent patterns. In contrast, Domain adaptation and Transfer learning methods are sub-fields within machine learning that are concerned with solving the inescapable problem of insufficient training data by relaxing the domain dependence hypothesis. In this contribution, this issue has been addressed and by making a novel combination of both the methods we develop a computationally efficient and practical algorithm to solve boundary value problems based on nonlinear partial differential equations. We adopt a meshfree analysis framework to integrate the prevailing geometric modelling techniques based on NURBS and present an enhanced deep collocation approach that also plays an important role in the accuracy of solutions. We start with a brief introduction on how these methods expand upon this framework. We observe an excellent agreement between these methods and have shown that how fine-tuning a pre-trained network to a specialized domain may lead to an outstanding performance compare to the existing ones. As proof of concept, we illustrate the performance of our proposed model on several benchmark problems.<\/jats:p>","DOI":"10.1007\/s00366-022-01661-2","type":"journal-article","created":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T11:04:16Z","timestamp":1653303856000},"page":"4569-4588","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Domain adaptation based transfer learning approach for solving PDEs on complex geometries"],"prefix":"10.1007","volume":"38","author":[{"given":"Ayan","family":"Chakraborty","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cosmin","family":"Anitescu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoying","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timon","family":"Rabczuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,5,23]]},"reference":[{"issue":"7","key":"1661_CR1","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Osindero S, Teh Y-W (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527\u20131554","journal-title":"Neural Comput"},{"key":"1661_CR2","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: Icml"},{"key":"1661_CR3","unstructured":"Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov RR, Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580"},{"key":"1661_CR4","unstructured":"Goodfellow I, Warde-Farley D, Mirza M, Courville A, Bengio Y (2013) Maxout networks. In: International conference on machine learning, PMLR, pp 1319\u20131327"},{"key":"1661_CR5","unstructured":"Agostinelli F, Hoffman M, Sadowski P, Baldi P, Learning activation functions to improve deep neural networks. arXiv preprint arXiv:1412.6830"},{"issue":"4","key":"1661_CR6","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/BF02478259","volume":"5","author":"WS McCulloch","year":"1943","unstructured":"McCulloch WS, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5(4):115\u2013133","journal-title":"Bull Math Biophys"},{"issue":"10","key":"1661_CR7","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2009","unstructured":"Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345\u20131359","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1661_CR8","doi-asserted-by":"crossref","unstructured":"Weiss KR, Khoshgoftaar TM (2016) An investigation of transfer learning and traditional machine learning algorithms. In: 2016 IEEE 28th international conference on tools with artificial intelligence (ICTAI), IEEE, pp 283\u2013290","DOI":"10.1109\/ICTAI.2016.0051"},{"key":"1661_CR9","doi-asserted-by":"publisher","first-page":"102447","DOI":"10.1016\/j.tafmec.2019.102447","volume":"106","author":"S Goswami","year":"2020","unstructured":"Goswami S, Anitescu C, Chakraborty S, Rabczuk T (2020) Transfer learning enhanced physics informed neural network for phase-field modeling of fracture. Theoret Appl Fract Mech 106:102447","journal-title":"Theoret Appl Fract Mech"},{"key":"1661_CR10","doi-asserted-by":"publisher","first-page":"109942","DOI":"10.1016\/j.jcp.2020.109942","volume":"426","author":"S Chakraborty","year":"2021","unstructured":"Chakraborty S (2021) Transfer learning based multi-fidelity physics informed deep neural network. J Comput Phys 426:109942","journal-title":"J Comput Phys"},{"key":"1661_CR11","unstructured":"Taylor ME, Stone P, Transfer learning for reinforcement learning domains: a survey. J Mach Learn Res 10(7)"},{"key":"1661_CR12","doi-asserted-by":"crossref","unstructured":"Ge L, Gao J, Zhang A (2013) Oms-tl: a framework of online multiple source transfer learning. In: Proceedings of the 22nd ACM international conference on information & knowledge management, pp 2423\u20132428","DOI":"10.1145\/2505515.2505603"},{"key":"1661_CR13","unstructured":"Ammar HB, Eaton E, Luna JM, Ruvolo P (2015) Autonomous cross-domain knowledge transfer in lifelong policy gradient reinforcement learning. In: Twenty-fourth international joint conference on artificial intelligence"},{"issue":"1","key":"1661_CR14","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1093\/nsr\/nwx105","volume":"5","author":"Y Zhang","year":"2018","unstructured":"Zhang Y, Yang Q (2018) An overview of multi-task learning. Natl Sci Rev 5(1):30\u201343","journal-title":"Natl Sci Rev"},{"key":"1661_CR15","doi-asserted-by":"publisher","first-page":"e7","DOI":"10.1017\/S0269888920000107","volume":"35","author":"F Shoeleh","year":"2020","unstructured":"Shoeleh F, Yadollahi MM, Asadpour M (2020) Domain adaptation-based transfer learning using adversarial networks. Knowl Eng Rev 35:e7","journal-title":"Knowl Eng Rev"},{"key":"1661_CR16","unstructured":"Kouw WM, Loog M, An introduction to domain adaptation and transfer learning. arXiv preprint arXiv:1812.11806"},{"key":"1661_CR17","unstructured":"Magill M, Qureshi F, de Haan H (2018) Neural networks trained to solve differential equations learn general representations. In: Advances in neural information processing systems, pp 4071\u20134081"},{"key":"1661_CR18","unstructured":"Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? In: Advances in neural information processing systems, pp 3320\u20133328"},{"key":"1661_CR19","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.knosys.2015.01.010","volume":"80","author":"J Lu","year":"2015","unstructured":"Lu J, Behbood V, Hao P, Zuo H, Xue S, Zhang G (2015) Transfer learning using computational intelligence: a survey. Knowl-Based Syst 80:14\u201323","journal-title":"Knowl-Based Syst"},{"key":"1661_CR20","unstructured":"Zhuang Z, Tan M, Zhuang B, Liu J, Guo Y, Wu Q, Huang J, Zhu J, Discrimination-aware channel pruning for deep neural networks. arXiv preprint arXiv:1810.11809"},{"key":"1661_CR21","doi-asserted-by":"crossref","unstructured":"Yim J, Joo D, Bae J, Kim J (2017) A gift from knowledge distillation: Fast optimization, network minimization and transfer learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4133\u20134141","DOI":"10.1109\/CVPR.2017.754"},{"key":"1661_CR22","doi-asserted-by":"crossref","unstructured":"Schaefferkoetter P, Michopoulos JG, Song JH (2021) Strong-form meshfree collocation method for non-equilibrium solidification of multi-component alloy. Eng Comput:1\u201315","DOI":"10.1007\/s00366-021-01503-7"},{"key":"1661_CR23","doi-asserted-by":"crossref","unstructured":"Beel A, Song J-H (2021) Strong-form meshfree collocation method for multibody thermomechanical contact. Eng Comput:1\u201320","DOI":"10.1007\/s00366-021-01513-5"},{"key":"1661_CR24","doi-asserted-by":"publisher","first-page":"113650","DOI":"10.1016\/j.cma.2020.113650","volume":"375","author":"Y-C Yoon","year":"2021","unstructured":"Yoon Y-C, Song J-H (2021) Interface immersed particle difference method for weak discontinuity in elliptic boundary value problems. Comput Methods Appl Mech Eng 375:113650","journal-title":"Comput Methods Appl Mech Eng"},{"key":"1661_CR25","unstructured":"Chakraborty A, Wick T, Zhuang X, Rabczuk T (2021) Multigoal-oriented dual-weighted-residual error estimation using deep neural networks. arXiv e-prints arXiv\u20132112"},{"issue":"3","key":"1661_CR26","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1002\/cnm.1640100303","volume":"10","author":"M Dissanayake","year":"1994","unstructured":"Dissanayake M, Phan-Thien N (1994) Neural-network-based approximations for solving partial differential equations. Commun Numer Methods Eng 10(3):195\u2013201","journal-title":"Commun Numer Methods Eng"},{"issue":"2","key":"1661_CR27","doi-asserted-by":"publisher","first-page":"108","DOI":"10.3390\/info11020108","volume":"11","author":"J Howard","year":"2020","unstructured":"Howard J, Gugger S (2020) Fastai: a layered api for deep learning. Information 11(2):108","journal-title":"Information"},{"key":"1661_CR28","unstructured":"Howard J, Ruder S, Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146"},{"issue":"16","key":"1661_CR29","doi-asserted-by":"publisher","first-page":"2629","DOI":"10.1140\/epjst\/e2020-000098-9","volume":"229","author":"S Saha","year":"2020","unstructured":"Saha S, Nagaraj N, Mathur A, Yedida R, Sneha H (2020) Evolution of novel activation functions in neural network training for astronomy data: habitability classification of exoplanets. Eur Phys J Spec Top 229(16):2629\u20132738","journal-title":"Eur Phys J Spec Top"},{"key":"1661_CR30","doi-asserted-by":"publisher","first-page":"112790","DOI":"10.1016\/j.cma.2019.112790","volume":"362","author":"E Samaniego","year":"2020","unstructured":"Samaniego E, Anitescu C, Goswami S, Nguyen-Thanh VM, Guo H, Hamdia K, Zhuang X, Rabczuk T (2020) An energy approach to the solution of partial differential equations in computational mechanics via machine learning: concepts, implementation and applications. Comput Methods Appl Mech Eng 362:112790","journal-title":"Comput Methods Appl Mech Eng"},{"key":"1661_CR31","unstructured":"Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M et al (2016) Tensorflow: a system for large-scale machine learning. In: 12th $$\\{$$USENIX$$\\}$$ symposium on operating systems design and implementation ($$\\{$$OSDI$$\\}$$ 16), pp 265\u2013283"},{"key":"1661_CR32","unstructured":"Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics, JMLR Workshop and Conference Proceedings, pp 249\u2013256"},{"issue":"2","key":"1661_CR33","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/0893-6080(91)90009-T","volume":"4","author":"K Hornik","year":"1991","unstructured":"Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Netw 4(2):251\u2013257","journal-title":"Neural Netw"},{"key":"1661_CR34","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1016\/j.jcp.2018.08.029","volume":"375","author":"J Sirignano","year":"2018","unstructured":"Sirignano J, Spiliopoulos K (2018) Dgm: a deep learning algorithm for solving partial differential equations. J Comput Phys 375:1339\u20131364","journal-title":"J Comput Phys"},{"issue":"39\u201341","key":"1661_CR35","doi-asserted-by":"publisher","first-page":"4135","DOI":"10.1016\/j.cma.2004.10.008","volume":"194","author":"TJ Hughes","year":"2005","unstructured":"Hughes TJ, Cottrell JA, Bazilevs Y (2005) Isogeometric analysis: cad, finite elements, nurbs, exact geometry and mesh refinement. Comput Methods Appl Mech Eng 194(39\u201341):4135\u20134195","journal-title":"Comput Methods Appl Mech Eng"},{"key":"1661_CR36","doi-asserted-by":"publisher","DOI":"10.1002\/9780470749081","volume-title":"Isogeometric analysis: toward integration of CAD and FEA","author":"JA Cottrell","year":"2009","unstructured":"Cottrell JA, Hughes TJ, Bazilevs Y (2009) Isogeometric analysis: toward integration of CAD and FEA. Wiley, New York"},{"key":"1661_CR37","volume-title":"The NURBS book","author":"L Piegl","year":"1996","unstructured":"Piegl L, Tiller W (1996) The NURBS book. Springer, Berlin"},{"key":"1661_CR38","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.matcom.2015.05.008","volume":"117","author":"VP Nguyen","year":"2015","unstructured":"Nguyen VP, Anitescu C, Bordas SP, Rabczuk T (2015) Isogeometric analysis: an overview and computer implementation aspects. Math Comput Simul 117:89\u2013116","journal-title":"Math Comput Simul"},{"issue":"9\u201311","key":"1661_CR39","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1016\/S0965-9978(98)00110-0","volume":"30","author":"E Dimas","year":"1999","unstructured":"Dimas E, Briassoulis D (1999) 3d geometric modelling based on nurbs: a review. Adv Eng Softw 30(9\u201311):741\u2013751","journal-title":"Adv Eng Softw"},{"key":"1661_CR40","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.softx.2018.12.005","volume":"9","author":"OR Bingol","year":"2019","unstructured":"Bingol OR, Krishnamurthy A (2019) Nurbs-python: an open-source object-oriented nurbs modeling framework in python. SoftwareX 9:85\u201394","journal-title":"SoftwareX"},{"key":"1661_CR41","unstructured":"Wilson AC, Roelofs R, Stern M, Srebro N, Recht B, The marginal value of adaptive gradient methods in machine learning. arXiv preprint arXiv:1705.08292"},{"key":"1661_CR42","unstructured":"Keskar NS, Socher R, Improving generalization performance by switching from adam to sgd. arXiv preprint arXiv:1712.07628"},{"key":"1661_CR43","unstructured":"Reddi SJ, Kale S, Kumar S, On the convergence of adam and beyond. arXiv preprint arXiv:1904.09237"},{"issue":"3","key":"1661_CR44","doi-asserted-by":"publisher","first-page":"A681","DOI":"10.1137\/16M1067792","volume":"39","author":"I Toulopoulos","year":"2017","unstructured":"Toulopoulos I, Wick T (2017) Numerical methods for power-law diffusion problems. SIAM J Sci Comput 39(3):A681\u2013A710","journal-title":"SIAM J Sci Comput"},{"issue":"2","key":"1661_CR45","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1006\/jmaa.1993.1319","volume":"178","author":"W Liu","year":"1993","unstructured":"Liu W, Barrett JW (1993) A remark on the regularity of the solutions of the p-laplacian and its application to their finite element approximation. J Math Anal Appl 178(2):470\u2013487","journal-title":"J Math Anal Appl"},{"key":"1661_CR46","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-09620-9","volume-title":"An introduction to the mathematical theory of the Navier-Stokes equations: steady-state problems","author":"G Galdi","year":"2011","unstructured":"Galdi G (2011) An introduction to the mathematical theory of the Navier-Stokes equations: steady-state problems. Springer, Berlin"},{"key":"1661_CR47","unstructured":"Zhang W, Deng L, Wu D, Overcoming negative transfer: a survey. arXiv preprint arXiv:2009.00909"},{"key":"1661_CR48","doi-asserted-by":"crossref","unstructured":"Wang Z, Dai Z, P\u00f3czos B, Carbonell J (2019) Characterizing and avoiding negative transfer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11293\u201311302","DOI":"10.1109\/CVPR.2019.01155"},{"key":"1661_CR49","unstructured":"Chen X, Wang S, Fu B, Long M, Wang J, Catastrophic forgetting meets negative transfer: batch spectral shrinkage for safe transfer learning"},{"issue":"13","key":"1661_CR50","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick J, Pascanu R, Rabinowitz N, Veness J, Desjardins G, Rusu AA, Milan K, Quan J, Ramalho T, Grabska-Barwinska A et al (2017) Overcoming catastrophic forgetting in neural networks. Proc Natl Acad Sci 114(13):3521\u20133526","journal-title":"Proc Natl Acad Sci"},{"key":"1661_CR51","unstructured":"Sutskever I, Martens J, Dahl G, Hinton G (2013) On the importance of initialization and momentum in deep learning. In: International conference on machine learning, PMLR, pp 1139\u20131147"},{"key":"1661_CR52","unstructured":"Zhou K, Jin Y, Ding Q, Cheng J (2020) Amortized Nesterov\u2019s momentum: a robust momentum and its application to deep learning. In: Conference on uncertainty in artificial intelligence, PMLR, pp 211\u2013220"},{"key":"1661_CR53","unstructured":"Liu C, Belkin M (2019) Accelerating sgd with momentum for over-parameterized learning. In: International conference on learning representations"}],"container-title":["Engineering with Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00366-022-01661-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00366-022-01661-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00366-022-01661-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T12:08:58Z","timestamp":1668254938000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00366-022-01661-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":53,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["1661"],"URL":"https:\/\/doi.org\/10.1007\/s00366-022-01661-2","relation":{},"ISSN":["0177-0667","1435-5663"],"issn-type":[{"value":"0177-0667","type":"print"},{"value":"1435-5663","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,23]]},"assertion":[{"value":"28 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 April 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}