{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T23:25:49Z","timestamp":1787095549384,"version":"build-2736575974"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100009757","name":"National Institute of Advanced Industrial Science and Technology","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100009757","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["New Gener. Comput."],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Neural architecture search (NAS) has recently gained significant attention in the field of AutoML, driven by advances in deep learning techniques. Although many existing NAS methods prioritize classification performance, they require a small architecture to operate effectively in memory-constrained environments. Because model size is a crucial factor in deep learning, NAS methods that balance model size and classification performance are essential. However, owing to their large architectural search spaces, conventional NAS methods tend to converge on large architectures and consume substantial computational resources. To address this issue, this study proposes a novel NAS method that introduces constraints on model size to reduce search time and computational cost. Specifically, our approach involves adjustments to the learning process to improve efficiency, rearranging algorithmic sequences, and integrating a technique called \u201cchange alpha\u2019s priority\u201d. Experimental results confirm that the proposed method can identify search for smaller network architectures than the original unconstrained NAS method while maintaining high classification accuracy. The proposed method can search for neural network architectures suitable for various devices and applications.<\/jats:p>","DOI":"10.1007\/s00354-026-00323-x","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T04:14:15Z","timestamp":1782706455000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Neural Architecture Search with Model-Size Constraints: A Gradient-Based Approach"],"prefix":"10.1007","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5570-5828","authenticated-orcid":false,"given":"Kazuki","family":"Hemmi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuki","family":"Tanigaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masaki","family":"Onishi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"323_CR1","unstructured":"R\u00a0OpenAI. Gpt-4 technical report. arXiv, pp. 2303\u201308774 (2023)"},{"key":"323_CR2","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","volume":"630","author":"J Abramson","year":"2024","unstructured":"Abramson, J., Adler, J., Dunger, J., Evans, R., Green, T., Pritzel, A., Ronneberger, O., Willmore, L., Ballard, A.J., Bambrick, J., et al.: Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630, 493\u2013500 (2024)","journal-title":"Nature"},{"key":"323_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856. (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"323_CR4","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. (2019) . (PMLR)"},{"issue":"1","key":"323_CR5","first-page":"1997","volume":"20","author":"T Elsken","year":"2019","unstructured":"Elsken, T., Metzen, J.H., Hutter, F.: Neural architecture search: a survey. J. Mach. Learn. Res. 20(1), 1997\u20132017 (2019)","journal-title":"J. Mach. Learn. Res."},{"key":"323_CR6","unstructured":"Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search, p. ICLR. (2018)"},{"key":"323_CR7","unstructured":"Yuhui, X., Xie, L., Zhang, X., Chen, X., Qi, G.-J., Tian, Q., Xiong, H.: PC-DARTS: partial channel connections for memory-efficient architecture search, p. ICLR. (2020)"},{"key":"323_CR8","unstructured":"Cai, H., Zhu, L., Han, S.: ProxylessNAS: direct neural architecture search on target task and hardware. In: International Conference on Learning Representations, (2019)"},{"key":"323_CR9","unstructured":"Bichen, W., Dai, X., Zhang, P., Wang, Y., Sun, F., Yiming, W., Tian, Y., Vajda, P., Jia, Y., Keutzer, K.: FBNet: hardware-aware efficient convnet design via differentiable neural architecture search. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10734\u201310742. (2019)"},{"key":"323_CR10","doi-asserted-by":"crossref","unstructured":"Hu, Y., Wu, X., He, R.: TF-NAS: rethinking three search freedoms of latency-constrained differentiable neural architecture search. In: European Conference on Computer Vision, pp. 123\u2013139. Springer (2020)","DOI":"10.1007\/978-3-030-58555-6_8"},{"key":"323_CR11","doi-asserted-by":"crossref","unstructured":"Dutta, O., Kanvar, T., Agarwal, S.: Search-time efficient device constraints-aware neural architecture search. In: International Conference on Pattern Recognition and Machine Intelligence, pp. 38\u201348. Springer (2023)","DOI":"10.1007\/978-3-031-45170-6_5"},{"key":"323_CR12","doi-asserted-by":"crossref","unstructured":"Cai, Z., Chen, L., Liu, P., Ling, T., Lai, Y.: EG-NAS: neural architecture search with fast evolutionary exploration. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 11159\u201311167. (2024)","DOI":"10.1609\/aaai.v38i10.28993"},{"issue":"4","key":"323_CR13","doi-asserted-by":"publisher","first-page":"692","DOI":"10.3390\/electronics13040692","volume":"13","author":"M Xiang","year":"2024","unstructured":"Xiang, M., Ding, R., Liu, H., Zhou, X.: Latency-constrained neural architecture search method for efficient model deployment on RISC-V devices. Electronics 13(4), 692 (2024)","journal-title":"Electronics"},{"key":"323_CR14","unstructured":"Hemmi, K., Tanigaki, Y., Onishi, M.: MC-DARTS: model size constrained differentiable architecture search. In: Has it Trained Yet? NeurIPS 2022 Workshop, (2022)"},{"key":"323_CR15","unstructured":"Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning, p. ICLR. (2016)"},{"key":"323_CR16","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition, pp. 8697\u20138710. CVPR (2018)","DOI":"10.1109\/CVPR.2018.00907"},{"issue":"1","key":"323_CR17","first-page":"1","volume":"18","author":"X Yan","year":"2017","unstructured":"Yan, X., Jia, Z., Wang, L.-B., Ai, Y., Zhang, F., Lai, M., Chang, E.I., et al.: Large scale tissue histopathology image classification, segmentation, and visualization via deep convolutional activation features. BMC Bioinform. 18(1), 1\u201317 (2017)","journal-title":"BMC Bioinform."},{"key":"323_CR18","unstructured":"Real, E., Moore, S., Selle, A., Saxena, S., Suematsu, Y.L., Tan, J., Le, Q.V., Kurakin, A.: Large-scale evolution of image classifiers. In: International Conference on Machine Learning, pp. 2902\u20132911. PMLR (2017)"},{"key":"323_CR19","doi-asserted-by":"crossref","unstructured":"Xie, L., Yuille, A.: Genetic CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1379\u20131388. (2017)","DOI":"10.1109\/ICCV.2017.154"},{"key":"323_CR20","doi-asserted-by":"crossref","unstructured":"Hou, P., Jin, Y., Chen, Y.: Single-DARTS: towards stable architecture search. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 373\u2013382. (2021)","DOI":"10.1109\/ICCVW54120.2021.00046"},{"key":"323_CR21","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.patrec.2023.10.019","volume":"176","author":"A Heuillet","year":"2023","unstructured":"Heuillet, A., Tabia, H., Arioui, H., Youcef-Toumi, K.: D-DARTS: distributed differentiable architecture search. Pattern Recognit. Lett. 176, 42\u201348 (2023)","journal-title":"Pattern Recognit. Lett."},{"key":"323_CR22","doi-asserted-by":"crossref","unstructured":"He, H., Liu, L., Zhang, H., Zheng, N.: IS-DARTS: stabilizing darts through precise measurement on candidate importance. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 12367\u201312375. (2024)","DOI":"10.1609\/aaai.v38i11.29128"},{"key":"323_CR23","unstructured":"Yu, J., Huang, T.: AutoSlim: towards one-shot architecture search for channel numbers, (2019). arXiv:1903.11728 arXiv preprint"},{"key":"323_CR24","unstructured":"Jin, X., Wang, J., Slocum, J., Yang, M.-H., Dai, S., Yan, S., Feng, J.: RC-DARTS: resource constrained differentiable architecture search, (2019). arXiv:1912.12814 arXiv preprint"},{"key":"323_CR25","unstructured":"Nayman, N., Aflalo, Y., Noy, A., Zelnik, L.: HardCoRe-NAS: hard constrained differentiable neural architecture search. In: International Conference on Machine Learning, pp. 7979\u20137990. (2021) . (PMLR)"},{"key":"323_CR26","doi-asserted-by":"crossref","unstructured":"Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., Le, Q.V.: MnasNet: platform-aware neural architecture search for mobile. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2820\u20132828. (2019)","DOI":"10.1109\/CVPR.2019.00293"},{"key":"323_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, L.L., Yang, Y., Jiang, Y., Zhu, W., Liu, Y.: Fast hardware-aware neural architecture search. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 692\u2013693. (2020)","DOI":"10.1109\/CVPRW50498.2020.00354"},{"key":"323_CR28","doi-asserted-by":"crossref","unstructured":"Elsken, T., Metzen, J.H., Hutter, F.: Efficient multi-objective neural architecture search via Lamarckian evolution, (2018). arXiv:1804.09081 arXiv preprint","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"323_CR29","doi-asserted-by":"crossref","unstructured":"Lu, Z., Whalen, I., Boddeti, V., Dhebar, Y., Deb, K., Goodman, E., Banzhaf, W.: NSGA-Net: neural architecture search using multi-objective genetic algorithm. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 419\u2013427. (2019)","DOI":"10.1145\/3321707.3321729"},{"key":"323_CR30","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.-C.,\u00a0Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., Vasudevan, V., et\u00a0al.: Searching for MobileNetV3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"323_CR31","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images, (2009)"},{"key":"323_CR32","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1007\/s11263-020-01396-x","volume":"129","author":"X Chen","year":"2021","unstructured":"Chen, X., Xie, L., Jun, W., Tian, Q.: Progressive DARTS: bridging the optimization gap for NAS in the wild. Int. J. Comput. Vis. 129, 638\u2013655 (2021)","journal-title":"Int. J. Comput. Vis."},{"issue":"9","key":"323_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3473330","volume":"54","author":"L Xie","year":"2021","unstructured":"Xie, L., Chen, X., Bi, K., Wei, L., Yuhui, X., Wang, L., Chen, Z., Xiao, A., Chang, J., Zhang, X., et al.: Weight-sharing neural architecture search: a battle to shrink the optimization gap. ACM Comput. Surv. (CSUR) 54(9), 1\u201337 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"323_CR34","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778. (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"323_CR35","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708. (2017)","DOI":"10.1109\/CVPR.2017.243"}],"container-title":["New Generation Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00354-026-00323-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00354-026-00323-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00354-026-00323-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T23:02:39Z","timestamp":1787094159000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00354-026-00323-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"references-count":35,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["323"],"URL":"https:\/\/doi.org\/10.1007\/s00354-026-00323-x","relation":{},"ISSN":["0288-3635","1882-7055"],"issn-type":[{"value":"0288-3635","type":"print"},{"value":"1882-7055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,29]]},"assertion":[{"value":"8 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no relevant financial or non-financial interests to disclose.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"22"}}