{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:02:52Z","timestamp":1783526572149,"version":"3.55.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T00:00:00Z","timestamp":1708041600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T00:00:00Z","timestamp":1708041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"H2020 Affordable5G EU Project","award":["957317"],"award-info":[{"award-number":["957317"]}]},{"DOI":"10.13039\/501100006470","name":"Aristotle University of Thessaloniki","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006470","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2024,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Deep Neural Networks (DNN) have made significant advances in various fields including speech recognition and image processing. Typically, modern DNNs are both compute and memory intensive, therefore their deployment in low-end devices is a challenging task. A well-known technique to address this problem is Low-Rank Factorization (LRF), where a weight tensor is approximated by one or more lower-rank tensors, reducing both the memory size and the number of executed tensor operations. However, the employment of LRF is a multi-parametric optimization process involving a huge design space where different design points represent different solutions trading-off the number of FLOPs, the memory size, and the prediction accuracy of the DNN models. As a result, extracting an efficient solution is a complex and time-consuming process. In this work, a new methodology is presented that formulates the LRF problem as a (FLOPs vs. memory vs. prediction accuracy) Design Space Exploration (DSE) problem. Then, the DSE space is drastically pruned by removing inefficient solutions. Our experimental results prove that the design space can be efficiently pruned, therefore extract only a limited set of solutions with improved accuracy, memory, and FLOPs compared to the original (non-factorized) model. Our methodology has been developed as a stand-alone, parameterized module integrated into T3F library of TensorFlow 2.X.<\/jats:p>","DOI":"10.1007\/s10766-024-00762-3","type":"journal-article","created":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T13:02:16Z","timestamp":1708088536000},"page":"20-39","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["A Practical Approach for Employing Tensor Train Decomposition in Edge Devices"],"prefix":"10.1007","volume":"52","author":[{"given":"Milad","family":"Kokhazadeh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgios","family":"Keramidas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vasilios","family":"Kelefouras","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iakovos","family":"Stamoulis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,16]]},"reference":[{"issue":"3","key":"762_CR1","doi-asserted-by":"publisher","first-page":"1686","DOI":"10.1109\/COMST.2020.2986444","volume":"22","author":"F Hussain","year":"2020","unstructured":"Hussain, F., Hussain, R., Hassan, S.A., Hossain, E.: Machine learning in IoT security: current solutions and future challenges. IEEE Commun. Surv. Tutor. 22(3), 1686\u20131721 (2020). https:\/\/doi.org\/10.1109\/COMST.2020.2986444","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"762_CR2","doi-asserted-by":"publisher","first-page":"3871","DOI":"10.1109\/JSEN.2019.2960701","volume":"20","author":"S Saraswat","year":"2020","unstructured":"Saraswat, S., Gupta, H.P., Dutta, T.: A writing activities monitoring system for preschoolers using a layered computing infrastructure. IEEE Sens. J. 20, 3871\u20133878 (2020). https:\/\/doi.org\/10.1109\/JSEN.2019.2960701","journal-title":"IEEE Sens. J."},{"key":"762_CR3","unstructured":"Mishra, A., Latorre, J.A., Pool, J., Stosic, D., Stosic, D., Venkatesh, G., Yu, C., Micikevicius, P.: Accelerating sparse deep neural networks. arXiv:2104.08378 (2021)"},{"key":"762_CR4","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1109\/TMSCS.2018.2864297","volume":"4","author":"AO Akmandor","year":"2018","unstructured":"Akmandor, A.O., YIN, H., Jha, N.K.: Smart, secure, yet energy-efficient, internet-of-things sensors. IEEE Trans. Multi-Scale Comput. Syst. 4, 914\u2013930 (2018). https:\/\/doi.org\/10.1109\/TMSCS.2018.2864297","journal-title":"IEEE Trans. Multi-Scale Comput. Syst."},{"key":"762_CR5","doi-asserted-by":"publisher","first-page":"052003","DOI":"10.1088\/1742-6596\/1213\/5\/052003","volume":"1213","author":"X Long","year":"2019","unstructured":"Long, X., Ben, Z., Liu, Y.: A survey of related research on compression and acceleration of deep neural networks. J. Phys. Conf. Ser. 1213, 052003 (2019). https:\/\/doi.org\/10.1088\/1742-6596\/1213\/5\/052003","journal-title":"J. Phys. Conf. Ser."},{"key":"762_CR6","unstructured":"Cheng, Y., Wang, D., Zhou, P., Zhang, T.: A survey of model compression and acceleration for deep neural networks. arXiv:1710.09282 (2017)"},{"key":"762_CR7","doi-asserted-by":"crossref","unstructured":"Pasandi, M.M., Hajabdollahi, M., Karimi, N., Samavi, S.: Modeling of pruning techniques for deep neural networks simplification. arXiv:2001.04062 (2020)","DOI":"10.1109\/MVIP49855.2020.9116891"},{"key":"762_CR8","doi-asserted-by":"crossref","unstructured":"Song, Z., Fu, B., Wu, F., Jiang, Z., Jiang, L., Jing, N., Liang, X.: DRQ: dynamic region-based quantization for deep neural network acceleration. In: ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA), 29 May\u20133 June 2020 (2020)","DOI":"10.1109\/ISCA45697.2020.00086"},{"key":"762_CR9","doi-asserted-by":"crossref","unstructured":"Huang, F., Zhang, L., Yang, Y., Zhou, X.: Probability weighted compact feature for domain adaptive retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 14\u201319 June 2020 (2020)","DOI":"10.1109\/CVPR42600.2020.00960"},{"key":"762_CR10","doi-asserted-by":"publisher","first-page":"1765","DOI":"10.1109\/TPDS.2020.3047003","volume":"32","author":"C Blakeney","year":"2021","unstructured":"Blakeney, C., Li, X., Yan, Y., Zong, Z.: Parallel Blockwise knowledge distillation for deep neural network compression. IEEE Trans. Parallel Distrib. Syst. 32, 1765\u20131776 (2021). https:\/\/doi.org\/10.1109\/TPDS.2020.3047003","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"762_CR11","doi-asserted-by":"crossref","unstructured":"Phan, A.-H., Sobolev, K., Sozykin, K., Ermilov, D., Gusak, J., Tichavsk\u1ef3, P., Glukhov, V., Oseledets, I., Cichocki, A.: Stable low-rank tensor decomposition for compression of convolutional neural network. In: European Conference on Computer Vision, 23\u201328 August 2020 (2020)","DOI":"10.1007\/978-3-030-58526-6_31"},{"key":"762_CR12","doi-asserted-by":"crossref","unstructured":"He, Y., Kang, G., Dong, X., Fu, Y., Yang, Y.: Soft filter pruning for accelerating deep convolutional neural networks. arXiv:1808.06866 (2018)","DOI":"10.24963\/ijcai.2018\/309"},{"key":"762_CR13","doi-asserted-by":"crossref","unstructured":"He, Y., Kang, G., Dong, X., Fu, Y., Yang, Y.: Channel pruning for accelerating very deep neural networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 22\u201329 October 2017 (2017)","DOI":"10.1109\/ICCV.2017.155"},{"key":"762_CR14","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems, 7\u201312 December 2017 (2015)"},{"key":"762_CR15","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou, J., Yu, B., Maybank, S.J.: Knowledge distillation: a survey. Int. J. Comput. Vis. 129, 1789\u20131819 (2021). https:\/\/doi.org\/10.1007\/s11263-021-01453-z","journal-title":"Int. J. Comput. Vis."},{"issue":"30","key":"762_CR16","first-page":"1","volume":"21","author":"A Novikov","year":"2020","unstructured":"Novikov, A., Izmailov, P., Khrulkov, V., Figurnov, M., Oseledets, I.V.: Tensor train decomposition on tensorflow (t3f). J. Mach. Learn. Res. 21(30), 1\u20137 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"762_CR17","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., others.: TensorFlow: a system for Large-Scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), 2\u20134 November 2016 (2016)"},{"key":"762_CR18","doi-asserted-by":"crossref","unstructured":"Kokhazadeh, M., Keramidas, G., Kelefouras, V., Stamoulis, I.: A Design space exploration methodology for enabling tensor train decomposition in edge devices. In: International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS XXII), 3\u20137 July 2022 (2022)","DOI":"10.1007\/978-3-031-15074-6_11"},{"key":"762_CR19","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Kingsbury, B., Sindhwani, V., Arisoy, E., Ramabhadran, B.: Low-rank matrix factorization for deep neural network training with high-dimensional output targets. In: IEEE International Conference on Acoustics, Speech and Signal Processing, 26\u201331 May 2013 (2013)","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"762_CR20","unstructured":"Zhang, J., Lei, Q., Dhillon, I.: Stabilizing gradients for deep neural networks via efficient SVD parameterization. In: Proceedings of the 35th International Conference on Machine Learning, 10\u201315 Jul 2018 (2018)"},{"key":"762_CR21","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.neunet.2020.04.021","volume":"128","author":"MM Bejani","year":"2020","unstructured":"Bejani, M.M., Ghatee, M.: Theory of adaptive SVD regularization for deep neural networks. Neural Netw. 128, 33\u201346 (2020). https:\/\/doi.org\/10.1016\/j.neunet.2020.04.021","journal-title":"Neural Netw."},{"key":"762_CR22","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.neucom.2020.02.035","volume":"398","author":"S Swaminathan","year":"2020","unstructured":"Swaminathan, S., Garg, D., Kannan, R., Andres, F.: Sparse low rank factorization for deep neural network compression. Neurocomputing 398, 185\u2013196 (2020). https:\/\/doi.org\/10.1016\/j.neucom.2020.02.035","journal-title":"Neurocomputing"},{"key":"762_CR23","unstructured":"Chorti, A., Picard, D.: Rate analysis and deep neural network detectors for SEFDM FTN systems. arXiv:2103.02306 (2021)"},{"key":"762_CR24","unstructured":"Ganev, I., van Laarhoven, T., Walters, R.: Universal approximation and model compression for radial neural networks. arXiv:2107.02550 (2021)"},{"key":"762_CR25","unstructured":"Chee, J., Renz, M., Damle, A., De Sa, C.: Pruning neural networks with interpolative decompositions. arXiv:2108.00065 (2021)"},{"key":"762_CR26","doi-asserted-by":"crossref","unstructured":"Chan, T.K., Chin, C.S., Li, Y.: Non-negative matrix factorization-convolutional neural network (NMF-CNN) for sound event detection. arXiv:2001.07874 (2020)","DOI":"10.33682\/50ef-dx29"},{"key":"762_CR27","doi-asserted-by":"crossref","unstructured":"Li, D., Wang, X., Kong, D.: Deeprebirth: Accelerating deep neural network execution on mobile devices. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2\u20137 February 2018 (2018)","DOI":"10.1609\/aaai.v32i1.11876"},{"key":"762_CR28","doi-asserted-by":"publisher","first-page":"107538","DOI":"10.1016\/j.patcog.2020.107538","volume":"110","author":"Z Bai","year":"2021","unstructured":"Bai, Z., Li, Y., Wo\u017aniak, M., Zhou, M., Li, D.: Decomvqanet: decomposing visual question answering deep network via tensor decomposition and regression. Pattern Recognit. 110, 107538 (2021). https:\/\/doi.org\/10.1016\/j.patcog.2020.107538","journal-title":"Pattern Recognit."},{"key":"762_CR29","doi-asserted-by":"crossref","unstructured":"Frusque, G., Michau, G., Fink, O.: Canonical Polyadic Decomposition and Deep Learning for Machine Fault Detection. arXiv:2107.09519 (2021)","DOI":"10.36001\/phme.2021.v6i1.2881"},{"key":"762_CR30","doi-asserted-by":"publisher","first-page":"1747","DOI":"10.1016\/j.patcog.2020.107538","volume":"2021","author":"R Ma","year":"2021","unstructured":"Ma, R., Lou, J., Li, P., Gao, J.: Reconstruction of generative adversarial networks in cross modal image generation with canonical polyadic decomposition. Wireless Commun. Mobile Comput. 2021, 1747\u20131756 (2021). https:\/\/doi.org\/10.1016\/j.patcog.2020.107538","journal-title":"Wireless Commun. Mobile Comput."},{"key":"762_CR31","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1137\/07070111X","volume":"51","author":"TG Kolda","year":"2009","unstructured":"Kolda, T.G., Bader, B.W.: Tensor decompositions and applications. SIAM Rev. 51, 455\u2013500 (2009). https:\/\/doi.org\/10.1137\/07070111X","journal-title":"SIAM Rev."},{"key":"762_CR32","doi-asserted-by":"crossref","unstructured":"Idelbayev, Y., Carreira-Perpinan, M.A.: Low-rank compression of neural nets: learning the rank of each layer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 14\u201319 June 2020 (2020)","DOI":"10.1109\/CVPR42600.2020.00807"},{"key":"762_CR33","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1137\/090752286","volume":"33","author":"IV Oseledets","year":"2011","unstructured":"Oseledets, I.V.: Tensor-train decomposition. SIAM J. Sci. Comput. 33, 2295\u20132317 (2011). https:\/\/doi.org\/10.1137\/090752286","journal-title":"SIAM J. Sci. Comput."},{"key":"762_CR34","unstructured":"Novikov, A., Podoprikhin, D., Osokin, A., Vetrov, D.P.: Tensorizing neural networks. In: Advances in Neural Information Processing Systems, Vol. 28 (2015)"},{"key":"762_CR35","doi-asserted-by":"publisher","first-page":"18","DOI":"10.3390\/econometrics9020018","volume":"9","author":"DSG Pollock","year":"2021","unstructured":"Pollock, D.S.G.: Multidimensional arrays, indices and Kronecker products. Econometrics 9, 18\u201333 (2021). https:\/\/doi.org\/10.3390\/econometrics9020018","journal-title":"Econometrics"},{"key":"762_CR36","doi-asserted-by":"publisher","DOI":"10.56021\/9781421407944","volume-title":"Matrix Computations","author":"GH Golub","year":"2013","unstructured":"Golub, G.H., Van Loan, C.F.: Matrix Computations. JHU Press, Baltimore (2013)"},{"key":"762_CR37","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1137\/21M1391444","volume":"4","author":"C Hawkins","year":"2022","unstructured":"Hawkins, C., Liu, X., Zhang, Z.: Towards compact neural networks via end-to-end training: A Bayesian tensor approach with automatic rank determination. SIAM J. Math. Data Sci. 4, 46\u201371 (2022). https:\/\/doi.org\/10.1137\/21M1391444","journal-title":"SIAM J. Math. Data Sci."},{"key":"762_CR38","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Li, B., Fan, Y., Bao, Y.: A novel rank selection scheme in tensor ring decomposition based on reinforcement learning for deep neural networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4\u20138 May 2020 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053292"},{"key":"762_CR39","doi-asserted-by":"publisher","first-page":"17605","DOI":"10.1109\/ACCESS.2020.2968357","volume":"8","author":"T Kim","year":"2020","unstructured":"Kim, T., Lee, J., Choe, Y.: Bayesian optimization-based global optimal rank selection for compression of convolutional neural networks. IEEE Access 8, 17605\u201317618 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.2968357","journal-title":"IEEE Access"},{"key":"762_CR40","unstructured":"LeCun, Y., others.: Lenet-5, convolutional neural networks. 20(5), 14 (2015). http:\/\/yann.lecun.com\/exdb\/lenet"},{"key":"762_CR41","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, vol. 25 (2012)"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-024-00762-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10766-024-00762-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-024-00762-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T09:06:17Z","timestamp":1711703177000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10766-024-00762-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,16]]},"references-count":41,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["762"],"URL":"https:\/\/doi.org\/10.1007\/s10766-024-00762-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2506533\/v1","asserted-by":"object"}]},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,16]]},"assertion":[{"value":"23 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}