Adaptive Curriculum Learning for Accelerating Convergence in Data-Driven Model Training
Article Sidebar
Curriculum Learning,
Machine Learning,
Model Convergence,
Training Efficiency
Main Article Content
Eko Risdianto
Muhammet Esad Kuloğlu
Maria Ulfa
Abstract
Background: Efficient training of machine learning models remains a critical challenge in data-driven artificial intelligence systems, particularly when training samples vary in difficulty, noise level, and representational complexity.
Aims: This study proposes and evaluates an adaptive curriculum learning framework that accelerates convergence in machine learning model training by dynamically adjusting sample ordering based on the model's evolving competence.
Methods: The proposed approach introduces a feedback-driven curriculum mechanism that integrates difficulty estimation and model competence evaluation. Training samples are initially ranked by estimated difficulty and are progressively updated during training using validation-based performance signals. Experiments are conducted on three benchmark datasets, including UCI Adult Income, Breast Cancer Wisconsin, and CIFAR-10, using multilayer perceptron and convolutional neural network architectures. The framework is compared against random sampling, static curriculum learning, and hard-first sampling strategies. Performance is evaluated based on convergence speed, predictive accuracy, robustness to noise, class imbalance handling, and computational overhead.
Result: The proposed adaptive curriculum learning framework consistently accelerates convergence across all datasets compared to baseline methods. The model achieves faster stabilization of training dynamics while maintaining or slightly improving predictive performance on accuracy, F1-score, and AUC. Furthermore, the framework demonstrates improved robustness under noisy-label conditions and class-imbalance scenarios, with reduced performance degradation compared to conventional sampling strategies. The computational overhead introduced by the adaptive mechanism remains minimal compared with the gains in training efficiency.
Conclusion: The study concludes that aligning sample ordering with evolving model competence significantly improves training efficiency in machine learning systems.
Article Details
Copyright (c) 2026 Eko Risdianto, Muhammet Esad Kuloğlu, Maria Ulfa
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
Al Bataineh, A., Kaur, D., & Jalali, S. M. J. (2022). Multi-Layer Perceptron Training Optimization Using Nature Inspired Computing. IEEE Access, 10, 36963–36977. https://doi.org/10.1109/ACCESS.2022.3164669
Altalhan, M., Algarni, A., & Turki-Hadj Alouane, M. (2025). Imbalanced Data Problem in Machine Learning: A Review. IEEE Access, 13, 13686–13699. https://doi.org/10.1109/ACCESS.2025.3531662
Bian, K., & Priyadarshi, R. (2024). Machine Learning Optimization Techniques: A Survey, Classification, Challenges, and Future Research Issues. Archives of Computational Methods in Engineering 2024 31:7, 31(7), 4209–4233. https://doi.org/10.1007/S11831-024-10110-W
Chaudhry, S., & Sharma, A. (2024). Data Distribution-Based Curriculum Learning. IEEE Access, 12, 138429–138440. https://doi.org/10.1109/ACCESS.2024.3465793
Chen, W., Yang, K., Yu, Z., Shi, Y., & Chen, C. L. P. (2024). A survey on imbalanced learning : latest research , applications and future directions. Artificial Intelligence Review (2024), 123(57). https://doi.org/10.1007/s10462-024-10759-6
Chen, Z., Zhang, J., Liu, B., Lin, F., & Yin, W. (2025). Scale Down to Speed Up: Dynamic Data Selection for Reinforcement Learning. EMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2025, 7806–7817. https://doi.org/10.18653/v1/2025.findings-emnlp.412
Dekker, R. B., Otto, F., & Summerfield, C. (2022). Curriculum learning for human compositional generalization. Proceedings of the National Academy of Sciences of the United States of America, 119(41), 1–12. https://doi.org/10.1073/pnas.2205582119
Demartini, C. G., Sciascia, L., Bosso, A., & Manuri, F. (2024). Artificial Intelligence Bringing Improvements to Adaptive Learning in Education: A Case Study. Sustainability 2024, Vol. 16, Page 1347, 16(3), 1347. https://doi.org/10.3390/SU16031347
Divya, S., Adepu, B., & Kamakshi, P. (2022). Image Enhancement And Classification Of Cifar-10 Using Convolutional Neural Networks. Proceedings - 4th International Conference on Smart Systems and Inventive Technology, ICSSIT 2022. https://doi.org/10.1109/ICSSIT53264.2022.9716555
Dritsas, E., & Trigka, M. (2025). Database Systems in the Big Data Era: Architectures , Performance , and Open Challenges. IEEE Access, 13(May), 95068–95084. https://doi.org/10.1109/ACCESS.2025.3572059
Feng, Q., Liu, Y., & Schütze, H. (2025). Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding. Proceedings of the Annual Meeting of the Association for Computational Linguistics, 4, 222–239. https://doi.org/10.18653/v1/2025.acl-srw.15
Ferrari, F. (2023). Skills mismatch and change confidence: the impact of training on change recipients’ self-efficacy. European Journal of Training and Development, 47(10), 69–90. https://doi.org/10.1108/EJTD-06-2021-0072
Ghosh, K., Bellinger, C., Corizzo, R., Branco, P., Krawczyk, B., & Japkowicz, N. (2022). The class imbalance problem in deep learning. Machine Learning 2022 113:7, 113(7), 4845–4901. https://doi.org/10.1007/S10994-022-06268-8
Gong, Y., Liu, G., Xue, Y., Li, R., & Meng, L. (2023). A survey on dataset quality in machine learning. Information and Software Technology, 162, 107268. https://doi.org/10.1016/j.infsof.2023.107268
Holzinger, A., Longo, L., Cangelosi, A., & Ser, J. Del. (2025). Research Frontiers in Machine Learning & Knowledge Extraction. Machine Learning and Knowledge Extraction 2026, Vol. 8, Page 6, 8(1), 6. https://doi.org/10.3390/MAKE8010006
Islam Jony, A., Kumar, A., & Arnob, B. (2024). Deep Learning Paradigms for Breast Cancer Diagnosis: A Comparative Study on Wisconsin Diagnostic Dataset. Malaysian Journal of Science and Advanced Technology, 4(2), 109–117. https://doi.org/10.56532/MJSAT.V4I2.245
Karakasidis, G., Kurimo, M., Bell, P., & Grósz, T. (2024). Comparison and analysis of new curriculum criteria for end-to-end ASR. Speech Communication, 163(May 2023), 103113. https://doi.org/10.1016/j.specom.2024.103113
Lalor, J. P., & Yu, H. (2020). Dynamic data selection for curriculum learning via ability estimation. Findings of the Association for Computational Linguistics Findings of ACL: EMNLP 2020, 9, 545–555. https://doi.org/10.18653/v1/2020.findings-emnlp.48
Li, S., Yang, B., & Zou, Y. (2022). Adaptive Curriculum Learning for Video Captioning. IEEE Access, 10, 31751–31759. https://doi.org/10.1109/ACCESS.2022.3160451
Liu, F., Zhang, T., Zhang, C., Liu, L., Wang, L., & Liu, B. (2023). A Review of the Evaluation System for Curriculum Learning. Electronics (Switzerland), 12(7). https://doi.org/10.3390/electronics12071676
Machado, M. de O. C., Bravo, N. F. S., Martins, A. F., Bernardino, H. S., Barrere, E., & Souza, J. F. de. (2021). Metaheuristic-based adaptive curriculum sequencing approaches: a systematic review and mapping of the literature. Artificial Intelligence Review, 54(1), 711–754. https://doi.org/10.1007/S10462-020-09864-Z/TABLES/13
Mosqueira-Rey, E., Hernández-Pereira, E., Alonso-Ríos, D., Bobes-Bascarán, J., & Fernández-Leal, Á. (2023). Human-in-the-loop machine learning: a state of the art. In Artificial Intelligence Review (Vol. 56, Number 4). Springer Netherlands. https://doi.org/10.1007/s10462-022-10246-w
Nunes, G. H., Martins, G. O., Forster, C. H. Q., & Lorena, A. C. (2021). Using instance hardness measures in curriculum learning. Anais Do Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), 18, 177–188. https://doi.org/10.5753/eniac.2021.18251
Saglietti, L., Mannelli, S. S., & Saxe, A. (2022). An Analytical Theory of Curriculum Learning in Teacher-Student Networks. Advances in Neural Information Processing Systems, 35. https://doi.org/10.1088/1742-5468/ac9b3c
Shen, L., Sun, Y., Yu, Z., Ding, L., Tian, X., & Tao, D. (2024a). On Efficient Training of Large-Scale Deep Learning Models. ACM Computing Surveys, 57(3). https://doi.org/10.1145/3700439;WGROUP:STRING:ACM
Shen, L., Sun, Y., Yu, Z., Ding, L., Tian, X., & Tao, D. (2024b). On Efficient Training of Large-Scale Deep Learning Models. ACM Computing Surveys, 57(3). https://doi.org/10.1145/3700439
Shi, P., & Liu, W. (2025). Adaptive learning oriented higher educational classroom teaching strategies. Scientific Reports 2025 15:1, 15(1), 15661-. https://doi.org/10.1038/s41598-025-00536-y
Shivashankar, K., Hajj, G. Al, & Martini, A. (2025). Maintainability and Scalability in Machine Learning: Challenges and Solutions. ACM Computing Surveys, 57(12). https://doi.org/10.1145/3736751;CSUBTYPE:STRING:JOURNAL;ISSUE:ISSUE:DOI
Shu, J., Yuan, X., & Meng, D. (2023). CMW-Net: an adaptive robust algorithm for sample selection and label correction. National Science Review, 10(6), 4–7. https://doi.org/10.1093/nsr/nwad084
Soviany, P., Ionescu, R. T., Rota, P., & Sebe, N. (2022). Curriculum Learning: A Survey. International Journal of Computer Vision 2022 130:6, 130(6), 1526–1565. https://doi.org/10.1007/S11263-022-01611-X
Talaei Khoei, T., & Kaabouch, N. (2023). Machine Learning: Models, Challenges, and Research Directions. Future Internet 2023, Vol. 15, Page 332, 15(10), 332. https://doi.org/10.3390/FI15100332
Tang, X., Xu, C., Tao, H., Ma, X., & Hou, C. (2025). Confidence-Based PU Learning With Instance-Dependent Label Noise. IEEE Transactions on Neural Networks and Learning Systems, 36(8), 14283–14297. https://doi.org/10.1109/TNNLS.2025.3549510
Ten, A., Kaushik, P., Oudeyer, P. Y., & Gottlieb, J. (2021). Humans monitor learning progress in curiosity-driven exploration. Nature Communications 2021 12:1, 12(1), 5972-. https://doi.org/10.1038/s41467-021-26196-w
Wang, X., Chen, Y., & Zhu, W. (2022). A Survey on Curriculum Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(9), 4555–4576.https://doi.org/10.1109/TPAMI.2021.3069908
Zhao, Y., Wang, Z., & Huang, Z. (2021). Automatic Curriculum Learning With Over-repetition Penalty for Dialogue Policy Learning. 35th AAAI Conference on Artificial Intelligence, AAAI 2021, 16, 14540–14548. https://doi.org/10.1609/aaai.v35i16.17709
Zheng, J., Qiu, S., Shi, C., & Ma, Q. (2025). Towards Lifelong Learning of Large Language Models: A Survey. ACM Computing Surveys, 57(8). https://doi.org/10.1145/3716629
Zhou, Z., Luo, J., Arefan, D., Kitamura, G., & Wu, S. (2023). Human Not in the Loop: Objective Sample Difficulty Measures for Curriculum Learning. Proceedings - International Symposium on Biomedical Imaging, 2023-April(Cl). https://doi.org/10.1109/ISBI53787.2023.10230597