Transfer Learning Effectiveness Across Domain Similarity Levels in Data Science Applications
Article Sidebar
Data Science,
Domain Similarity,
Model Adaptation,
Transfer Learning
Main Article Content
Eko Risdianto
Thai Ky Trung Pham
William Yeoh
Sultan Hammad Alshammari
Abstract
Background: Transfer learning has become increasingly prominent in data science due to the challenges posed by limited labeled data and distribution shifts between training and deployment environments. However, the success of transfer learning depends significantly on the structural compatibility between source and target domains.
Aims: This study aims to investigate the relationship between domain similarity and transfer learning performance using an experimental framework termed Similarity-Aware Transfer Evaluation (SATE).
Methods: Twelve pairs of benchmark datasets were selected to simulate varying levels of domain similarity and were made publicly available. Domain similarity was computed using Maximum Mean Discrepancy (MMD) in the learned representation space. Transfer performance was measured using a predefined Transfer Gain metric under bounded fine-tuning strategies. Correlation analysis and statistical testing were conducted to examine the relationship between similarity scores and transfer effectiveness, while fine-tuning depth was analyzed in relation to similarity magnitude.
Result: The results demonstrate a strong positive correlation between domain similarity and transfer gain (r = 0.83, p < 0.01), indicating that approximately 69% of performance variability can be explained by similarity-based transfer effects. Negative transfer was observed when similarity scores were S ≤ 0.41. Furthermore, higher similarity levels were associated with deeper and more stable fine-tuning, whereas lower similarity resulted in increased instability during adaptation. These findings establish similarity as a structural compatibility constraint in transfer learning.
Conclusion: The study confirms that domain similarity plays a fundamental role in determining transfer learning success. By operationalizing similarity measurement and linking it to performance thresholds, the proposed SATE framework provides a structured method for evaluating transfer feasibility in real-world data science applications.
Article Details
Copyright (c) 2026 Eko Risdianto, Thai Ky Trung Pham, William Yeoh, Sultan Hammad Alshammari
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
Ali, A. H., & Abdulazeez, A. M. (2024). Transfer Learning In Machine Learning: A Review Of Methods And Applications. Indonesian Journal of Computer Science, 13(1), 4227–4259. https://doi.org/10.33022/ijcs.v13i3.4068
Bai, D., & Ma, S. (2025). Performance Evaluation of Similarity Metrics in Transfer Learning for Building Heating Load Forecasting. Energies, 18(17), 1–14. https://doi.org/10.3390/en18174678
Căvescu, A. M., & Popescu, A. N. (2026). Leakage-Free Evaluation for Employee Attrition Prediction on Tabular Data. Information, 17(3). https://doi.org/10.3390/info17030308
Dan, J., Jin, T., Chi, H., C, S. D., Xie, H., Cao, K., & Yang, X. (2023). Trust-aware conditional adversarial domain adaptation with feature norm alignment. Neural Networks, 168, 518–530. https://doi.org/10.1016/j.neunet.2023.10.002
Davila, A. N. A., & Colan, J. (2025). Bio-Inspired Fine-Tuning for Selective Transfer Learning in Image Classification. IEEE Access, 13, 129234–129249. https://doi.org/10.1109/ACCESS.2025.3587524
Hosna, A., Merry, E., Gyalmo, J., Alom, Z., Aung, Z., & Azim, M. A. (2022). Transfer learning : a friendly introduction. Journal of Big Data, 9(102). https://doi.org/10.1186/s40537-022-00652-w
Javed, H., El-Sappagh, S., & Abuhmed, T. (2025). Robustness in deep learning models for medical diagnostics : security and adversarial challenges towards robust AI. Artificial Intelligence Review, 58(12). https://doi.org/10.1007/s10462-024-11005-9
Joeres, R., Blumenthal, D. B., & Kalinina, O. V. (2025). Data splitting to avoid information leakage with DataSAIL. Nature Communications, 16, 3337. https://doi.org/10.1038/s41467-025-58606-8
Khan, S., Yin, P., Guo, Y., Asim, M., & El-Latif, A. A. A. (2024). Heterogeneous transfer learning: recent developments, applications, and challenges. Multimedia Tools and Applications, 83(27), 69759–69795. https://doi.org/10.1007/s11042-024-18352-3
Lin, H., Ho, T., Tu, C., Lin, H., & Yu, C. (2025). MeTa Learning-Based Optimization of Unsupervised Domain Adaptation Deep Networks. Mathematics, 13(2), 1–23. https://doi.org/10.3390/math13020226
Mahn, D., & Poblete, C. (2023). Contextualizing the knowledge spillover theory of entrepreneurship : the Chilean paradox. Entrepreneurship & Regional Development, 35(1–2), 209–239. https://doi.org/10.1080/08985626.2022.2117418
Pak, H., & Paal, S. G. (2022). Evaluation of transfer learning models for predicting the lateral strength of reinforced concrete columns. Engineering Structures, 266, 114579. https://doi.org/10.1016/j.engstruct.2022.114579
Plested, J., Phiri, M., & Gedeon, T. (2026). Deep transfer learning for image classification : a survey. Artificial Intelligence Review, 59(100), 1–50. https://doi.org/10.1007/s10462-026-11491-z
Riyazuddin, G. N. P. K. (2025). AI-Based Dynamic Spectrum Prediction and Allocation for IoT Wireless Networks Using Python. International Journal of Human Computations and Intelligence, 4(6), 637–655. https://doi.org/10.5281/zenodo.17377265
Singhal, P., Walambe, R., Ramanna, S., & Kotecha, K. (2023). Domain Adaptation : Challenges , Methods , Datasets , and Applications. IEEE Access, 11, 6973–7020. https://doi.org/10.1109/ACCESS.2023.3237025
Tamang, L., Bouadjenek, M. R., Dazeley, R., & Aryal, S. (2025). Handling Out-of-Distribution Data: A Survey. IEEE Transactions on Knowledge and Data Engineering, 37(10), 5948–5966. https://doi.org/10.1109/TKDE.2025.3592614
Tang, W., Liu, J., Zhou, Y., & Ding, Z. (2024). Causality-Guided Counterfactual Debiasing for Anomaly Detection of Cyber-Physical Systems. IEEE Transactions on Industrial Informatics, 20(3), 4582–4593. https://doi.org/10.1109/TII.2023.3326544
Weiss, K., Khoshgoftaar, T. M., & Wang, D. (2016). A survey of transfer learning. In Journal of Big Data. Springer International Publishing. https://doi.org/10.1186/s40537-016-0043-6
Woesle, C., Fischer-brandies, L., Buettner, R., & Member, S. (2025). A Systematic Literature Review of Hallucinations in Large Language Models. IEEE Access, 13, 148231–148253. https://doi.org/10.1109/ACCESS.2025.3601206
Xu, J., Li, D., Zhou, P., Zhang, Y., Wang, Z., & Ma, D. (2024). A Relation Feature Comparison Network for Cross-Domain Recognition of Motion Intention. IEEE Transactions on Instrumentation and Measurement, 73, 4008513. https://doi.org/10.1109/TIM.2024.3420350
Yan, P., Abdulkadir, A., Luley, P., Rosenthal, M., Schatte, G. A., & Grewe, B. F. (2024). A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series : Methods , Applications , and Directions. IEEE Access, 12, 3768–3789. https://doi.org/10.1109/ACCESS.2023.3349132
Yu, S., Song, L., Pang, S., Wang, M., He, X., & Xie, P. (2024). M-Net : a novel unsupervised domain adaptation framework based on multi-kernel maximum mean discrepancy for fault diagnosis of rotating machinery. Complex & Intelligent Systems, 10(3), 3259–3272. https://doi.org/10.1007/s40747-023-01320-z
Zhang, G., Feng, L., Chen, X., Tang, K., & Tan, K. C. (2026). Enhancing Reinforcement Learning With Cross-Domain Knowledge Transfer via Seeded Graph Matching. IEEE Transactions on Neural Networks and Learning Systems, 37(1), 371–385. https://doi.org/10.1109/TNNLS.2025.3606751
Zhao, C., Zhao, H., Zhu, H., Huang, Z., Feng, N., & Chen, E. (2024). Bi-Discriminator Domain Adversarial Neural Networks With Class-Level Gradient Alignment. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 54(9), 5283–5295. https://doi.org/10.1109/TSMC.2024.3402750
Zhu, Z., Yan, Y., Li, G., & Zhang, R. (2025). Recent Developments on Statistical Transfer Learning. International Statistical Review. https://doi.org/10.1111/insr.12613