{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T03:34:54Z","timestamp":1784086494643,"version":"3.55.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007069","name":"Universit\u00e0 della Calabria","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007069","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Training deep neural networks (DNNs) is increasingly recognized as a major contributor to the energy footprint of Artificial Intelligence (AI). Existing dataset pruning (DP) and active learning (AL) techniques reduce training data volumes but often introduce costly computations that undermine their energy-saving potential. This paper introduces\n                    <jats:italic>Play it Straight<\/jats:italic>\n                    and its enhanced variant\n                    <jats:italic>Re-Play it Straight<\/jats:italic>\n                    , two adaptive training algorithms that combine random subset sampling with lightweight AL-inspired instance selection. The proposed framework achieves a better balance between accuracy and energy efficiency by incrementally fine-tuning models on small, informative subsets, while controlling computational overhead. Experiments on multiple benchmark datasets demonstrate substantial reductions in training energy compared to state-of-the-art DP and AL methods, with\n                    <jats:italic>Re-Play it Straight<\/jats:italic>\n                    consistently delivering superior performance. These results highlight the potential of our approach to support more sustainable deep learning practices, contributing to the broader goals of Green AI.\n                  <\/jats:p>","DOI":"10.1007\/s10994-025-06907-w","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T19:59:22Z","timestamp":1762891162000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An efficient model training framework for green AI"],"prefix":"10.1007","volume":"114","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5224-0910","authenticated-orcid":false,"given":"Francesco","family":"Scala","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4164-940X","authenticated-orcid":false,"given":"Sergio","family":"Flesca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4513-0362","authenticated-orcid":false,"given":"Luigi","family":"Pontieri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"6907_CR1","unstructured":"Ash, J.T., Goel, S., Krishnamurthy, A., & Kakade, S.M. (2021). Gone fishing: Neural active learning with fisher embeddings. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, Virtual, pp. 8927\u20138939"},{"key":"6907_CR2","unstructured":"Ayed, F., & Hayou, S. (2023). Data pruning and neural scaling laws: fundamental limitations of score-based algorithms. Trans. Mach. Learn. Res. 2023"},{"issue":"122","key":"6907_CR3","first-page":"1","volume":"24","author":"BR Bartoldson","year":"2023","unstructured":"Bartoldson, B. R., Kailkhura, B., & Blalock, D. (2023). Compute-efficient deep learning: algorithmic trends and opportunities. Journal of Machine Learning Research, 24(122), 1\u201377.","journal-title":"Journal of Machine Learning Research"},{"key":"6907_CR4","doi-asserted-by":"publisher","unstructured":"Botev, A., Lever, G., & Barber, D. (2017). Nesterov\u2019s accelerated gradient and momentum as approximations to regularised update descent. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 1899\u20131903 . https:\/\/doi.org\/10.1109\/IJCNN.2017.7966082","DOI":"10.1109\/IJCNN.2017.7966082"},{"key":"6907_CR5","unstructured":"Chang, H.-S., Learned-Miller, E.G., & McCallum, A. (2017). Active bias: Training more accurate neural networks by emphasizing high variance samples. In: Neural Information Processing Systems . https:\/\/api.semanticscholar.org\/CorpusID:20785832"},{"key":"6907_CR6","unstructured":"Coleman, C., Yeh, C., Mussmann, S., Mirzasoleiman, B., Bailis, P., Liang, P., Leskovec, J., & Zaharia, M. (2020). Selection via proxy: Efficient data selection for deep learning. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net, ??? . https:\/\/openreview.net\/forum?id=HJg2b0VYDr"},{"key":"6907_CR7","doi-asserted-by":"publisher","unstructured":"Courty, B., Schmidt, V., Luccioni, S., Goyal-Kamal, MarionCoutarel, Feld, B., Lecourt, J., LiamConnell, Saboni, A., Inimaz, supatomic, L\u00e9val, M., Blanche, L., Cruveiller, A., ouminasara, Zhao, F., Joshi, A., Bogroff, A., Lavoreille, H., Laskaris, N., Abati, E., Blank, D., Wang, Z., Catovic, A., Alencon, M., Stechly, M., Bauer, C., & Lucas-Otavio, JPW, (2024). MinervaBooks: mlco2\/codecarbon: v2.4.1. Zenodo . https:\/\/doi.org\/10.5281\/zenodo.11171501 .","DOI":"10.5281\/zenodo.11171501"},{"key":"6907_CR8","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 . https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6907_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116936","volume":"200","author":"S Flesca","year":"2022","unstructured":"Flesca, S., Scala, F., Vocaturo, E., & Zumpano, F. (2022). On forecasting non-renewable energy production with uncertainty quantification: A case study of the italian energy market. Expert Systems with Applications, 200, Article 116936. https:\/\/doi.org\/10.1016\/j.eswa.2022.116936","journal-title":"Expert Systems with Applications"},{"key":"6907_CR10","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.jpdc.2019.07.007","volume":"134","author":"E Garcia-Martin","year":"2019","unstructured":"Garcia-Martin, E., Rodrigues, C. F., Riley, G., & Grahn, H. (2019). Estimation of energy consumption in machine learning. Journal of Parallel and Distributed Computing, 134, 75\u201388. https:\/\/doi.org\/10.1016\/j.jpdc.2019.07.007","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"6907_CR11","unstructured":"Goujaud, B., Scieur, D., Dieuleveut, A., Taylor, A.B., & Pedregosa, F. (2022). Super-acceleration with cyclical step-sizes. In: Camps-Valls, G., Ruiz, F.J.R., Valera, I. (eds.) Proceedings of The 25th International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol. 151, pp. 3028\u20133065. PMLR, ??? . https:\/\/proceedings.mlr.press\/v151\/goujaud22a.html"},{"key":"6907_CR12","doi-asserted-by":"publisher","unstructured":"Guo, C., Zhao, B., & Bai, Y. (2022). Deepcore: A comprehensive library for coreset selection in deep learning. In: Database and Expert Systems Applications: 33rd International Conference, DEXA 2022, Vienna, Austria, August 22\u201324, 2022, Proceedings, Part I, pp. 181\u2013195. Springer, Berlin, Heidelberg . https:\/\/doi.org\/10.1007\/978-3-031-12423-5_14","DOI":"10.1007\/978-3-031-12423-5_14"},{"key":"6907_CR13","unstructured":"Haimovich, D., Karamshuk, D., Linder, F., Tax, N., & Vojnovic, M. (2024). On the convergence of loss and uncertainty-based active learning algorithms. In: Globersons, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J.M., Zhang, C. (eds.) Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024"},{"key":"6907_CR14","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 . https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"6907_CR15","unstructured":"Huang, G., Li, Y., Pleiss, G., Liu, Z., Hopcroft, J.E., & Weinberger, K.Q. (2017). Snapshot ensembles: Train 1, get M for free. CoRR abs\/1704.00109 arXiv:1704.00109"},{"key":"6907_CR16","unstructured":"Iyer, R., Khargoankar, N., Bilmes, J., & Asanani, H. (2021). Submodular combinatorial information measures with applications in machine learning. In: Feldman, V., Ligett, K., Sabato, S. (eds.) Proceedings of the 32nd International Conference on Algorithmic Learning Theory. Proceedings of Machine Learning Research, vol. 132, pp. 722\u2013754. PMLR, ??? . https:\/\/proceedings.mlr.press\/v132\/iyer21a.html"},{"key":"6907_CR17","unstructured":"Iyer, R.K., Khargoankar, N., Bilmes, J.A., & Asanani, H. (2021). Submodular combinatorial information measures with applications in machine learning. In: Feldman, V., Ligett, K., Sabato, S. (eds.) Algorithmic Learning Theory, 16-19 March 2021, Virtual Conference, Worldwide. Proceedings of Machine Learning Research, vol. 132, pp. 722\u2013754. PMLR, ??? . http:\/\/proceedings.mlr.press\/v132\/iyer21a.html"},{"key":"6907_CR18","unstructured":"Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D.P., & Wilson, A.G. (2018). Averaging weights leads to wider optima and better generalization. In: Globerson, A., Silva, R. (eds.) Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence, UAI 2018, Monterey, California, USA, August 6-10, 2018, pp. 876\u2013885. AUAI Press, ??? . http:\/\/auai.org\/uai2018\/proceedings\/papers\/313.pdf"},{"key":"6907_CR19","unstructured":"Katharopoulos, A., & Fleuret, F. (2018). Not all samples are created equal: Deep learning with importance sampling. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 2525\u20132534. PMLR, ??? . https:\/\/proceedings.mlr.press\/v80\/katharopoulos18a.html"},{"key":"6907_CR20","unstructured":"Krizhevsky, A., Nair, V., & Hinton, G. (2009) Cifar-10 (canadian institute for advanced research)"},{"key":"6907_CR21","unstructured":"Loo, N., Hasani, R., Amini, A., & Rus, D. (2022). Efficient dataset distillation using random feature approximation. In: Oh, A.H., Agarwal, A., Belgrave, D., Cho, K. (eds.) Advances in Neural Information Processing Systems . https:\/\/openreview.net\/forum?id=h8Bd7Gm3muB"},{"key":"6907_CR22","unstructured":"Loshchilov, I., & Hutter, F. (2017). SGDR: stochastic gradient descent with warm restarts. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net, ??? . https:\/\/openreview.net\/forum?id=Skq89Scxx"},{"key":"6907_CR23","unstructured":"Mirzasoleiman, B., Bilmes, J., & Leskovec, J. (2020). Coresets for data-efficient training of machine learning models. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 6950\u20136960. PMLR, ??? . https:\/\/proceedings.mlr.press\/v119\/mirzasoleiman20a.html"},{"key":"6907_CR24","unstructured":"Okanovic, P., Waleffe, R., Mageirakos, V., Nikolakakis, K., Karbasi, A., Kalogerias, D., G\u00fcrel, N.M., & Rekatsinas, T. (2024). Repeated random sampling for minimizing the time-to-accuracy of learning. In: The Twelfth International Conference on Learning Representations . https:\/\/openreview.net\/forum?id=JnRStoIuTe"},{"key":"6907_CR25","unstructured":"Park, D., Papailiopoulos, D., & Lee, K. (2022). Active learning is a strong baseline for data subset selection. In: Has It Trained Yet? NeurIPS 2022 Workshop"},{"key":"6907_CR26","unstructured":"Patterson, D.A., Gonzalez, J., Le, Q.V., Liang, C., Mungu\u00eda, L.-M., Rothchild, D., So, D.R., Texier, M., & Dean, J.(2021). Carbon emissions and large neural network training. ArXiv abs\/2104.10350"},{"key":"6907_CR27","unstructured":"Paul, M., Ganguli, S., & Dziugaite, G.K. (2021). Deep learning on a data diet: Finding important examples early in training. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems . https:\/\/openreview.net\/forum?id=Uj7pF-D-YvT"},{"key":"6907_CR28","doi-asserted-by":"publisher","unstructured":"Quercia, A., Morrison, A., Scharr, H., & Assent, I. (2023). Sgd biased towards early important samples for efficient training. In: 2023 IEEE International Conference on Data Mining (ICDM), pp. 1289\u20131294 . https:\/\/doi.org\/10.1109\/ICDM58522.2023.00163","DOI":"10.1109\/ICDM58522.2023.00163"},{"key":"6907_CR29","unstructured":"Sachdeva, N., Wu, C.-J., & McAuley, J. (2021). SVP-CF: Selection via Proxy for Collaborative Filtering Data . https:\/\/arxiv.org\/abs\/2107.04984"},{"key":"6907_CR30","unstructured":"Sachdeva, N., McAuley, J.J.: Data distillation: A survey. CoRR abs\/2301.04272(2023) https:\/\/doi.org\/10.48550\/ARXIV.2301.04272 2301.04272"},{"key":"6907_CR31","doi-asserted-by":"publisher","unstructured":"Salehi, S., & Schmeink, A. (2023). Is active learning green? an empirical study. In: 2023 IEEE International Conference on Big Data (BigData), pp. 3823\u20133829. IEEE Computer Society, Los Alamitos, CA, USA . https:\/\/doi.org\/10.1109\/BigData59044.2023.10386411","DOI":"10.1109\/BigData59044.2023.10386411"},{"key":"6907_CR32","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-031-78977-9_5","volume-title":"Discovery Science","author":"F Scala","year":"2025","unstructured":"Scala, F., Flesca, S., & Pontieri, L. (2025). Play it straight: an intelligent data pruning technique for green-ai. In D. Pedreschi, A. Monreale, R. Guidotti, R. Pellungrini, & F. Naretto (Eds.), Discovery Science (pp. 69\u201385). Cham: Springer."},{"key":"6907_CR33","unstructured":"Scala, F., Flesca, S., & Pontieri, L. (2024). Data filtering for a sustainable model training. In: Proceedings of the 32nd Symposium of Advanced Database Systems, Villasimius, Italy, June 23rd to 26th, 2024. CEUR Workshop Proceedings, vol. 3741, pp. 205\u2013216. CEUR-WS.org, ??? . https:\/\/ceur-ws.org\/Vol-3741\/paper26.pdf"},{"key":"6907_CR34","unstructured":"Sener, O., Savarese, S. (2017). Active learning for convolutional neural networks: A core-set approach. arXiv preprint arXiv:1708.00489"},{"key":"6907_CR35","unstructured":"Settles, B. (2009) Active Learning Literature Survey. Technical report, University of Wisconsin-Madison Department of Computer Sciences"},{"key":"6907_CR36","doi-asserted-by":"publisher","unstructured":"Smith, L.N. (2017). Cyclical learning rates for training neural networks. In: 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017, Santa Rosa, CA, USA, March 24-31, 2017, pp. 464\u2013472. IEEE Computer Society, ??? . https:\/\/doi.org\/10.1109\/WACV.2017.58 .","DOI":"10.1109\/WACV.2017.58"},{"key":"6907_CR37","doi-asserted-by":"publisher","unstructured":"Strubell, E., Ganesh, A., & McCallum, A. (2019). Energy and policy considerations for deep learning in NLP. In: Korhonen, A., Traum, D.R., M\u00e0rquez, L. (eds.) Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pp. 3645\u20133650. Association for Computational Linguistics, ??? . https:\/\/doi.org\/10.18653\/V1\/P19-1355 .","DOI":"10.18653\/V1\/P19-1355"},{"issue":"10","key":"6907_CR38","doi-asserted-by":"publisher","first-page":"2191","DOI":"10.1016\/j.joule.2023.09.004","volume":"7","author":"A de Vries","year":"2023","unstructured":"de Vries, A. (2023). The growing energy footprint of artificial intelligence. Joule, 7(10), 2191\u20132194. https:\/\/doi.org\/10.1016\/j.joule.2023.09.004","journal-title":"Joule"},{"key":"6907_CR39","doi-asserted-by":"crossref","unstructured":"Wang, K., Zhao, B., Peng, X., Zhu, Z., Yang, S., Wang, S., Huang, G., Bilen, H.,Wang, X., You, Y.: Cafe learning to condense dataset by aligning features. In:Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and PatternRecognition (CVPR), United States, pp. 12186\u201312195 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01188 . https:\/\/cvpr2022.thecvf.com\/","DOI":"10.1109\/CVPR52688.2022.01188"},{"key":"6907_CR40","unstructured":"Xu, J., Zhou, W., Fu, Z., Zhou, H., & Li, L.(2021). A survey on green deep learning. ArXiv abs\/2111.05193"},{"key":"6907_CR41","doi-asserted-by":"publisher","unstructured":"Yang, J., Tan, J., Wang, H., Chen, G., Wu, S., & Zhao, J. (2025). Shift guided active learning. Mach. Learn. 114(2) https:\/\/doi.org\/10.1007\/s10994-024-06684-y","DOI":"10.1007\/s10994-024-06684-y"},{"key":"6907_CR42","unstructured":"Yang, Z., Yang, H., Majumder, S., Cardoso, J., & Gallego, G. (2024). Data pruning can do more: A comprehensive data pruning approach for object re-identification. Transactions on Machine Learning Research"},{"issue":"01","key":"6907_CR43","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1109\/TPAMI.2023.3323376","volume":"46","author":"R Yu","year":"2024","unstructured":"Yu, R., Liu, S., & Wang, X. (2024). Dataset distillation: a comprehensive review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(01), 150\u2013170. https:\/\/doi.org\/10.1109\/TPAMI.2023.3323376","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"6907_CR44","unstructured":"Zhao, B., Mopuri, K.R., & Bilen, H.(2021). Dataset condensation with gradient matching. In: International Conference on Learning Representations . https:\/\/openreview.net\/forum?id=mSAKhLYLSsl"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06907-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06907-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06907-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T21:30:03Z","timestamp":1766439003000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06907-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":44,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["6907"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06907-w","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,11]]},"assertion":[{"value":"3 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 September 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no competing interests as defined by Springer, or other interests that might be perceived to influence the results and\/or discussion reported in this paper","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"We declare that this research did not require Ethics approval","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval and consent to participate"}},{"value":"All the authors of this manuscript consent to its publication","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"275"}}