{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T20:06:50Z","timestamp":1784318810050,"version":"3.55.0"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."],"published-print":{"date-parts":[[2024,11,21]]},"abstract":"<jats:p>Non-intrusive load monitoring (NILM) is crucial to smart grid, which enables applications such as energy conservation and human activity recognition. As a typical task of NILM, energy disaggregation is to decompose total power consumption into appliance-level ones. Despite the remarkable achievements of deep-learning-based methods, their training phase still requires intrusively collected appliance-level power data as strong labels, which are directly used for supervising predictions.<\/jats:p>\n          <jats:p>In this paper, we present ESATED, a novel energy disaggregation system which instead utilizes non-intrusively collected binary on-off states of appliances as labels, thus enhancing non-intrusiveness throughout the life cycle. However, our labels are inherently weak labels due to the weak correlation between labels (binary states) and predictions (real-valued power), thus making our model struggle in terms of feasible supervision and acceptable performance. To tackle this challenge, we first explore the feasibility of binary-state-based weak supervision, and then integrate it into an auxiliary learning system, where an auxiliary subtask (i.e., state classification) is introduced to further enhance the performance of the primary task (i.e., energy disaggregation). We conduct extensive experiments on two real-world public datasets, and also implement the prototype system in a practical scenario. Corresponding results reveal that even using weak labels, ESATED could achieve performance and transferability second only to the state-of-the-art model. This result demonstrates the effectiveness of the proposed approach to extract information and train the model from extra weak labels.<\/jats:p>","DOI":"10.1145\/3699729","type":"journal-article","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T12:23:32Z","timestamp":1732191812000},"page":"1-32","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["ESATED: Leveraging Extra-weak Supervision with Auxiliary Task for Enhanced Non-intrusiveness in Energy Disaggregation"],"prefix":"10.1145","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9889-3805","authenticated-orcid":false,"given":"Peng","family":"Xia","sequence":"first","affiliation":[{"name":"University of Science and Technology of China and Deqing Alpha Innovation Institute, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7545-6745","authenticated-orcid":false,"given":"Hao","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China and Deqing Alpha Innovation Institute, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4699-9874","authenticated-orcid":false,"given":"Tianjian","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Edinburgh, Edinburgh, United Kingdom and University of Science and Technology of China, Heifei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2915-4324","authenticated-orcid":false,"given":"Wangqiu","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China and Deqing Alpha Innovation Institute, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0537-4522","authenticated-orcid":false,"given":"Zhi","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Electro-Communications, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1240-4953","authenticated-orcid":false,"given":"Xiaoyan","family":"Wang","sequence":"additional","affiliation":[{"name":"Ibaraki University, Hitachi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6070-6625","authenticated-orcid":false,"given":"Xiang-Yang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China and Deqing Alpha Innovation Institute, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"NILM applications: Literature review of learning approaches, recent developments and challenges. Energy and Buildings","author":"Angelis Georgios-Fotios","year":"2022","unstructured":"Georgios-Fotios Angelis, Christos Timplalexis, Stelios Krinidis, Dimosthenis Ioannidis, and Dimitrios Tzovaras. 2022. NILM applications: Literature review of learning approaches, recent developments and challenges. Energy and Buildings (2022), 111951."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2019.2953225"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3027491"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3427771.3427859"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3148297"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943604"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.192069"},{"key":"e_1_2_1_8_1","volume-title":"d.]. Deep Learning Based Energy Disaggregation and On\/Off Detection of Household Appliances. arXiv","author":"Jiang J","year":"2019","unstructured":"J Jiang, Q Kong, M Plumbley, and N Gilbert. [n. d.]. Deep Learning Based Energy Disaggregation and On\/Off Detection of Household Appliances. arXiv 2019. arXiv preprint arXiv:1908.00941 ([n. d.])."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2923742"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2821650.2821672"},{"key":"e_1_2_1_11_1","volume-title":"The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes. Scientific data 2, 1","author":"Kelly Jack","year":"2015","unstructured":"Jack Kelly and William Knottenbelt. 2015. The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes. Scientific data 2, 1 (2015), 1--14."},{"key":"e_1_2_1_12_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491","author":"Kendall Alex","year":"2018","unstructured":"Alex Kendall, Yarin Gal, and Roberto Cipolla. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1620545.1620582"},{"key":"e_1_2_1_14_1","volume-title":"Workshop on data mining applications in sustainability (SIGKDD)","volume":"25","author":"Zico Kolter J","year":"2011","unstructured":"J Zico Kolter and Matthew J Johnson. 2011. REDD: A public data set for energy disaggregation research. In Workshop on data mining applications in sustainability (SIGKDD), San Diego, CA, Vol. 25. Citeseer, 59--62."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3200947.3201011"},{"key":"e_1_2_1_16_1","unstructured":"Yiming Li and Liao Qu. [n. d.]. NeuralNILM Pytorch. https:\/\/github.com\/Ming-er\/NeuralNILM_Pytorch."},{"key":"e_1_2_1_17_1","volume-title":"Auxiliary tasks in multi-task learning. arXiv preprint arXiv.1805.06334","author":"Liebel Lukas","year":"2018","unstructured":"Lukas Liebel and Marco K\u00f6rner. 2018. Auxiliary tasks in multi-task learning. arXiv preprint arXiv.1805.06334 (2018)."},{"key":"e_1_2_1_18_1","volume-title":"Self-supervised generalisation with meta auxiliary learning. Advances in Neural Information Processing Systems 32","author":"Liu Shikun","year":"2019","unstructured":"Shikun Liu, Andrew Davison, and Edward Johns. 2019. Self-supervised generalisation with meta auxiliary learning. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3139395"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2871620"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPAC49953.2019.237865"},{"key":"e_1_2_1_22_1","volume-title":"Transferability of Neural Network Approaches for Low-rate Energy Disaggregation. In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 8330--8334","author":"Murray David","year":"2019","unstructured":"David Murray, Lina Stankovic, Vladimir Stankovic, Srdjan Lulic, and Srdjan Sladojevic. 2019. Transferability of Neural Network Approaches for Low-rate Energy Disaggregation. In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 8330--8334."},{"key":"e_1_2_1_23_1","volume-title":"Auxiliary learning by implicit differentiation. arXiv preprint arXiv:2007.02693","author":"Navon Aviv","year":"2020","unstructured":"Aviv Navon, Idan Achituve, Haggai Maron, Gal Chechik, and Ethan Fetaya. 2020. Auxiliary learning by implicit differentiation. arXiv preprint arXiv:2007.02693 (2020)."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/PerCom.2013.6526716"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.636"},{"key":"e_1_2_1_26_1","volume-title":"An overview of multi-task learning in deep neural networks. arXiv preprint arXiv.1706.05098","author":"Ruder Sebastian","year":"2017","unstructured":"Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. arXiv preprint arXiv.1706.05098 (2017)."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2017.06.042"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2602044.2602058"},{"key":"e_1_2_1_29_1","volume-title":"Non-Intrusive Load Monitoring: A Review","author":"Schirmer Pascal A","year":"2022","unstructured":"Pascal A Schirmer and Iosif Mporas. 2022. Non-Intrusive Load Monitoring: A Review. IEEE Transactions on Smart Grid (2022)."},{"key":"e_1_2_1_30_1","volume-title":"Multi-task learning as multi-objective optimization. Advances in neural information processing systems 31","author":"Sener Ozan","year":"2018","unstructured":"Ozan Sener and Vladlen Koltun. 2018. Multi-task learning as multi-objective optimization. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909747"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011150"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/SEGE.2018.8499441"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"e_1_2_1_35_1","volume-title":"Sequence to sequence learning with neural networks. Advances in neural information processing systems 27","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2584581"},{"key":"e_1_2_1_37_1","volume-title":"Weakly Supervised Transfer Learning for Multi-label Appliance Classification. In International Conference on Applied Intelligence and Informatics. Springer, 360--375","author":"Tanoni Giulia","year":"2022","unstructured":"Giulia Tanoni, Emanuele Principi, Luigi Mandolini, and Stefano Squartini. 2022. Weakly Supervised Transfer Learning for Multi-label Appliance Classification. In International Conference on Applied Intelligence and Informatics. Springer, 360--375."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3191908"},{"key":"e_1_2_1_39_1","volume-title":"Partial label learning: Taxonomy, analysis and outlook. Neural Networks","author":"Tian Yingjie","year":"2023","unstructured":"Yingjie Tian, Xiaotong Yu, and Saiji Fu. 2023. Partial label learning: Taxonomy, analysis and outlook. Neural Networks (2023)."},{"key":"e_1_2_1_40_1","volume-title":"A comprehensive review on the nilm algorithms for energy disaggregation. arXiv preprint arXiv:2102.12578","author":"Verma Akriti","year":"2021","unstructured":"Akriti Verma, Adnan Anwar, MA Mahmud, Mohiuddin Ahmed, and Abbas Kouzani. 2021. A comprehensive review on the nilm algorithms for energy disaggregation. arXiv preprint arXiv:2102.12578 (2021)."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/SECON52354.2021.9491624"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/IWQOS52092.2021.9521262"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2955470"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11873"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACAIT56212.2022.10137966"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3087696"},{"key":"e_1_2_1_47_1","volume-title":"A brief introduction to weakly supervised learning. National science review 5, 1","author":"Zhou Zhi-Hua","year":"2018","unstructured":"Zhi-Hua Zhou. 2018. A brief introduction to weakly supervised learning. National science review 5, 1 (2018), 44--53."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610905"}],"container-title":["Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3699729","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3699729","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T16:25:28Z","timestamp":1758817528000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3699729"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"references-count":48,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,11,21]]}},"alternative-id":["10.1145\/3699729"],"URL":"https:\/\/doi.org\/10.1145\/3699729","relation":{},"ISSN":["2474-9567"],"issn-type":[{"value":"2474-9567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"2024-11-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}