{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T04:08:57Z","timestamp":1768450137679,"version":"3.49.0"},"reference-count":40,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2021,8,28]],"date-time":"2021-08-28T00:00:00Z","timestamp":1630108800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003170","name":"Stiftelsen f\u00f6r Kunskaps- och Kompetensutveckling","doi-asserted-by":"publisher","award":["2014\/0032"],"award-info":[{"award-number":["2014\/0032"]}],"id":[{"id":"10.13039\/501100003170","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Network"],"abstract":"<jats:p>The development of Quality of Experience (QoE) models using Machine Learning (ML) is challenging, since it can be difficult to share datasets between research entities to protect the intellectual property of the ML model and the confidentiality of user studies in compliance with data protection regulations such as General Data Protection Regulation (GDPR). This makes distributed machine learning techniques that do not necessitate sharing of data or attribute names appealing. One suitable use case in the scope of QoE can be the task of mapping QoE indicators for the perception of quality such as Mean Opinion Scores (MOS), in a distributed manner. In this article, we present Distributed Ensemble Learning (DEL), and Vertical Federated Learning (vFL) to address this context. Both approaches can be applied to datasets that have different feature sets, i.e., split features. The DEL approach is ML model-agnostic and achieves up to 12% accuracy improvement of ensembling various generic and specific models. The vFL approach is based on neural networks and achieves on-par accuracy with a conventional Fully Centralized machine learning model, while exhibiting statistically significant performance that is superior to that of the Isolated local models with an average accuracy improvement of 26%. Moreover, energy-efficient vFL with reduced network footprint and training time is obtained by further tuning the model hyper-parameters.<\/jats:p>","DOI":"10.3390\/network1020011","type":"journal-article","created":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T03:13:17Z","timestamp":1630465997000},"page":"165-190","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["QoE Modeling on Split Features with Distributed Deep Learning"],"prefix":"10.3390","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7594-2663","authenticated-orcid":false,"given":"Selim","family":"Ickin","sequence":"first","affiliation":[{"name":"Ericsson AB, 164 83 Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Markus","family":"Fiedler","sequence":"additional","affiliation":[{"name":"Department of Technology and Aesthetics (DITE), Blekinge Institute of Technology, 374 24 Karlshamn, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6925-0954","authenticated-orcid":false,"given":"Konstantinos","family":"Vandikas","sequence":"additional","affiliation":[{"name":"Ericsson AB, 164 83 Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,8,28]]},"reference":[{"key":"ref_1","unstructured":"Le Callet, P., M\u00f6ller, S., and Perkis, A. (2021, May 18). Qualinet White Paper on Definitions of Quality of Experience. European Network on Quality of Experience in Multimedia Systems and Services (COST Action IC 1003) 2012; Volume 3. Available online: http:\/\/www.qualinet.eu\/index.php?option=com_content&view=article&id=45&Itemid=52."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"117897","DOI":"10.1109\/ACCESS.2019.2936470","article-title":"Why is multimedia Quality of Experience assessment a challenging problem?","volume":"7","author":"Akhtar","year":"2019","journal-title":"IEEE Access"},{"key":"ref_3","unstructured":"Matinmikko-Blue, M., Aalto, S., Asghar, M.I., Berndt, H., Chen, Y., Dixit, S., Jurva, R., Karppinen, P., Kekkonen, M., and Kinnula, M. (2021, June 21). White Paper on 6G drivers and the UN SDGs. White Paper. Available online: https:\/\/arxiv.org\/abs\/2004.14695."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Alharbi, H.A., El-Gorashi, T.E.H., and Elmirghani, J.M.H. (2019, January 9\u201313). Energy efficient virtual machine services placement in cloud-fog architecture. Proceedings of the 2019 21st International Conference on Transparent Optical Networks (ICTON), Angers, France.","DOI":"10.1109\/ICTON.2019.8840258"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Sogaard, J., Forchhammer, S., and Brunnstr\u00f6m, K. (2015, January 26\u201329). Quality assessment of adaptive bitrate videos using image metrics and machine learning. Proceedings of the 2015 7th International Workshop on Quality of Multimedia Experience (QoMEX), Messinia, Greece.","DOI":"10.1109\/QoMEX.2015.7148105"},{"key":"ref_6","unstructured":"Wang, Z., Dai, Z., P\u00f3czos, B., and Carbonell, J. (2021, June 28). Characterizing and Avoiding Negative Transfer. Available online: https:\/\/arxiv.org\/abs\/1811.09751."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1109\/MWC.2015.7054716","article-title":"User privacy and data trustworthiness in mobile crowd sensing","volume":"22","author":"He","year":"2015","journal-title":"IEEE Wirel. Comm."},{"key":"ref_8","first-page":"30","article-title":"A survey on distributed machine learning","volume":"53","author":"Verbraeken","year":"2020","journal-title":"ACM Comput. Surv."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"4641","DOI":"10.1109\/JIOT.2020.2964162","article-title":"Federated learning with cooperating devices: A consensus approach for massive IoT networks","volume":"7","author":"Savazzi","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_10","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., and Arcas, B.A. (2017, January 20\u201322). Communication-efficient learning of deep networks from decentralized data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, Lauderdale, FL, USA."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ickin, S., Vandikas, K., and Fiedler, M. (2019, January 21). Privacy preserving QoE modeling using collaborative learning. Proceedings of the 4th QoE-Based Analysis and Management of Data Communication Networks, Los Cabos, Mexico.","DOI":"10.1145\/3349611.3355548"},{"key":"ref_12","unstructured":"Vepakomma, P., Gupta, O., Swedish, T., and Raskar, R. (2018). Split learning for health: Distributed deep learning without sharing raw patient data. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1145\/3298981","article-title":"Federated machine learning: Concept and applications","volume":"10","author":"Yang","year":"2019","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","author":"Wolpert","year":"1992","journal-title":"Neural Netw."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and sufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"Ann. Math. Statist."},{"key":"ref_16","unstructured":"Ryffel, T., Trask, A., Dahl, M., Wagner, B., Mancuso, J., Rueckert, D., and Passerat-Palmbach, J. (2018). A generic framework for privacy preserving deep learning. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_18","unstructured":"Bui, D., Malik, K., Goetz, J., Liu, H., Moon, S., Kumar, A., and Shin, K.G. (2021, June 28). Federated User Representation Learning. Available online: https:\/\/arxiv.org\/abs\/1909.12535."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/MMUL.2018.2879590","article-title":"Emotion-aware video QoE assessment via transfer learning","volume":"26","author":"Hao","year":"2019","journal-title":"IEEE Multimed."},{"key":"ref_20","unstructured":"(2021, June 28). Baidu All Reduce. Available online: https:\/\/github.com\/baidu-research\/baidu-allreduce."},{"key":"ref_21","first-page":"105","article-title":"Paddlepaddle: An open-source deep learning platform from industrial practice","volume":"1","author":"Ma","year":"2019","journal-title":"Front. Data Comput."},{"key":"ref_22","first-page":"1","article-title":"Federated learning","volume":"13","author":"Yang","year":"2019","journal-title":"Synth. Lect. Artif. Intell. Mach. Learn."},{"key":"ref_23","unstructured":"He, C., Li, S., So, J., Zeng, X., Zhang, M., Wang, H., Wang, X., Vepakomma, P., Singh, A., and Qiu, H. (2020). FedML: A research library and benchmark for federated machine learning. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhu, L., Liu, Z., and Han, S. (2019). Deep leakage from gradients. arXiv.","DOI":"10.1007\/978-3-030-63076-8_2"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Dwork, C. (2011). Differential privacy. Automata, Languages and Programming, Springer.","DOI":"10.1007\/978-1-4419-5906-5_752"},{"key":"ref_26","unstructured":"Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H.B., Patel, S., Ramage, D., Segal, A., and Seth, K. (\u20133, January 30). Practical secure aggregation for privacy-preserving machine learning. Proceedings of the ACM SIGSAC Conference on Computer and Communications Security (CCS\u201917), New York, NY, USA."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1109\/TIT.1975.1055349","article-title":"Universal codeword sets and representations of the integers","volume":"21","author":"Elias","year":"1975","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_28","unstructured":"(2021, June 28). PyArrow LZ4 Codec. Available online: https:\/\/arrow.apache.org\/docs\/python\/generated\/pyarrow.compress.html."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Casas, P., D\u2019Alconzo, A., Wamser, F., Seufert, M., Gardlo, B., Schwind, A., Tran-Gia, P., and Schatz, R. (June, January 29). Predicting QoE in cellular networks using machine learning and in-smartphone measurements. Proceedings of the 2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX), Erfurt, Germany.","DOI":"10.1109\/QoMEX.2017.7965687"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Robitza, W., G\u00f6ring, S., Raake, A., Lindegren, D., Heikkil\u00e4, G., Gustafsson, J., List, P., Feiten, B., W\u00fcstenhagen, U., and Garcia, M.-N. (2018, January 12\u201315). HTTP adaptive streaming QoE estimation with ITU-T rec. P. 1203: Open databases and software. Proceedings of the 9th ACM Multimedia Systems Conference, Amsterdam, The Netherlands.","DOI":"10.1145\/3204949.3208124"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1109\/TBC.2018.2822870","article-title":"A Quality-of-Experience database for adaptive video streaming","volume":"64","author":"Duanmu","year":"2018","journal-title":"IEEE Trans. Broadcast."},{"key":"ref_32","unstructured":"Robitza, W., Garcia, M.-N., and Raake, A. (June, January 31). A modular HTTP adaptive streaming QoE model\u2014Candidate for ITU-T P.1203 (\u2018P. NATS\u2019). Proceedings of the IEEE International Conference Quality of Multimedia Experience (QoMEX), Erfurt, Germany."},{"key":"ref_33","unstructured":"(2021, June 28). ITU-T P.910, Subjective Video Quality Assessment Methods for Multimedia Applications. Available online: https:\/\/www.itu.int\/rec\/T-REC-P.910-200804-I."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_35","unstructured":"Lundberg, S.M., and Lee, S.-I. (, January 4\u20139). A unified approach to interpreting model predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS\u201917), Long Beach, CA, USA."},{"key":"ref_36","first-page":"1","article-title":"QoE beyond the MOS: An in-depth look at QoE via better metrics and their relation to MOS","volume":"1","author":"Heegaard","year":"2016","journal-title":"Qual. User Exp."},{"key":"ref_37","unstructured":"(2021, June 28). Post Hoc Pairwise Test. Available online: https:\/\/scikit-posthocs.readthedocs.io\/en\/latest\/generated\/scikit_posthocs.posthoc_dunn\/."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/0885-2308(87)90026-X","article-title":"Learning sets of filters using back-propagation","volume":"2","author":"Plaut","year":"1987","journal-title":"Comput. Speech Lang."},{"key":"ref_39","unstructured":"(2021, June 28). RabbitMQ. Available online: https:\/\/www.rabbitmq.com\/."},{"key":"ref_40","unstructured":"(2021, June 28). EarlyStopping. Available online: https:\/\/keras.io\/api\/callbacks\/early_stopping\/."}],"container-title":["Network"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2673-8732\/1\/2\/11\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:54:25Z","timestamp":1760165665000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2673-8732\/1\/2\/11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,28]]},"references-count":40,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,9]]}},"alternative-id":["network1020011"],"URL":"https:\/\/doi.org\/10.3390\/network1020011","relation":{},"ISSN":["2673-8732"],"issn-type":[{"value":"2673-8732","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,28]]}}}