{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T06:56:12Z","timestamp":1781592972333,"version":"3.54.5"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012294","name":"National Social Science Fund Youth Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012294","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.engappai.2026.115209","type":"journal-article","created":{"date-parts":[[2026,5,31]],"date-time":"2026-05-31T14:38:01Z","timestamp":1780238281000},"page":"115209","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["Learning set representations with self-supervised masked transformer"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9447-6370","authenticated-orcid":false,"given":"Chen","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.115209_b1","doi-asserted-by":"crossref","unstructured":"Achituve, I., Maron, H., Chechik, G., 2021. Self-supervised learning for domain adaptation on point clouds. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 123\u2013133.","DOI":"10.1109\/WACV48630.2021.00017"},{"issue":"8","key":"10.1016\/j.engappai.2026.115209_b2","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1038\/nbt.3300","article-title":"Predicting the sequence specificities of DNA-and RNA-binding proteins by deep learning","volume":"33","author":"Alipanahi","year":"2015","journal-title":"Nature Biotechnol."},{"key":"10.1016\/j.engappai.2026.115209_b3","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"10.1016\/j.engappai.2026.115209_b4","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1023\/A:1009715923555","article-title":"A tutorial on support vector machines for pattern recognition","volume":"2","author":"Burges","year":"1998","journal-title":"Data Min. Knowl. Discov."},{"key":"10.1016\/j.engappai.2026.115209_b5","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"issue":"5","key":"10.1016\/j.engappai.2026.115209_b6","doi-asserted-by":"crossref","first-page":"2502","DOI":"10.1016\/j.eswa.2014.09.038","article-title":"Set-valued samples based support vector regression and its applications","volume":"42","author":"Chen","year":"2015","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.115209_b7","series-title":"Set-valued classification\u2013overview via a unified framework","author":"Chzhen","year":"2021"},{"key":"10.1016\/j.engappai.2026.115209_b8","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K., 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.engappai.2026.115209_b9","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A., 2015. Unsupervised visual representation learning by context prediction. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 1422\u20131430.","DOI":"10.1109\/ICCV.2015.167"},{"key":"10.1016\/j.engappai.2026.115209_b10","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.engappai.2026.115209_b11","series-title":"2023 62nd IEEE Conference on Decision and Control","first-page":"5325","article-title":"Set-valued regression and cautious suboptimization: from noisy data to optimality","author":"Eising","year":"2023"},{"issue":"2","key":"10.1016\/j.engappai.2026.115209_b12","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cogn. Sci."},{"issue":"10.5555","key":"10.1016\/j.engappai.2026.115209_b13","first-page":"2969239","article-title":"Towards real-time object detection with region proposal networks","volume":"9199","author":"Faster","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115209_b14","doi-asserted-by":"crossref","unstructured":"Fey, M., Lenssen, J.E., Weichert, F., M\u00fcller, H., 2018. Splinecnn: Fast geometric deep learning with continuous b-spline kernels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 869\u2013877.","DOI":"10.1109\/CVPR.2018.00097"},{"key":"10.1016\/j.engappai.2026.115209_b15","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R., 2022. Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10.1016\/j.engappai.2026.115209_b16","doi-asserted-by":"crossref","unstructured":"Hu, Z., Dong, Y., Wang, K., Chang, K.-W., Sun, Y., 2020. Gpt-gnn: Generative pre-training of graph neural networks. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. pp. 1857\u20131867.","DOI":"10.1145\/3394486.3403237"},{"key":"10.1016\/j.engappai.2026.115209_b17","series-title":"International Conference on Machine Learning","first-page":"2127","article-title":"Attention-based deep multiple instance learning","author":"Ilse","year":"2018"},{"key":"10.1016\/j.engappai.2026.115209_b18","article-title":"Exploiting generative models in discriminative classifiers","volume":"11","author":"Jaakkola","year":"1998","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"Jul","key":"10.1016\/j.engappai.2026.115209_b19","first-page":"819","article-title":"Probability product kernels","volume":"5","author":"Jebara","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2026.115209_b20","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1162\/tacl_a_00300","article-title":"Spanbert: Improving pre-training by representing and predicting spans","volume":"8","author":"Joshi","year":"2020","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.engappai.2026.115209_b21","unstructured":"Kondor, R., Jebara, T., 2003. A kernel between sets of vectors. In: Proceedings of the 20th International Conference on Machine Learning (ICML-03). pp. 361\u2013368."},{"key":"10.1016\/j.engappai.2026.115209_b22","series-title":"International Conference on Machine Learning","first-page":"957","article-title":"From word embeddings to document distances","author":"Kusner","year":"2015"},{"issue":"11","key":"10.1016\/j.engappai.2026.115209_b23","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.engappai.2026.115209_b24","series-title":"International Conference on Machine Learning","first-page":"3744","article-title":"Set transformer: A framework for attention-based permutation-invariant neural networks","author":"Lee","year":"2019"},{"issue":"1","key":"10.1016\/j.engappai.2026.115209_b25","first-page":"857","article-title":"Self-supervised learning: Generative or contrastive","volume":"35","author":"Liu","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.engappai.2026.115209_b26","series-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"10.1016\/j.engappai.2026.115209_b27","doi-asserted-by":"crossref","unstructured":"Monti, F., Boscaini, D., Masci, J., Rodola, E., Svoboda, J., Bronstein, M.M., 2017. Geometric deep learning on graphs and manifolds using mixture model cnns. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 5115\u20135124.","DOI":"10.1109\/CVPR.2017.576"},{"key":"10.1016\/j.engappai.2026.115209_b28","series-title":"Janossy pooling: Learning deep permutation-invariant functions for variable-size inputs","author":"Murphy","year":"2018"},{"key":"10.1016\/j.engappai.2026.115209_b29","series-title":"Set representation learning with generalized sliced-wasserstein embeddings","author":"Naderializadeh","year":"2021"},{"key":"10.1016\/j.engappai.2026.115209_b30","series-title":"European Conference on Computer Vision","first-page":"69","article-title":"Unsupervised learning of visual representations by solving jigsaw puzzles","author":"Noroozi","year":"2016"},{"key":"10.1016\/j.engappai.2026.115209_b31","first-page":"35021","article-title":"Learning neural set functions under the optimal subset oracle","volume":"35","author":"Ou","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115209_b32","series-title":"Quantum Chemistry in the Age of Machine Learning","first-page":"205","article-title":"Kernel methods","author":"Pinheiro Jr.","year":"2023"},{"key":"10.1016\/j.engappai.2026.115209_b33","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J., 2017. Pointnet: Deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 652\u2013660."},{"key":"10.1016\/j.engappai.2026.115209_b34","series-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"10.1016\/j.engappai.2026.115209_b35","series-title":"Group equivariant stand-alone self-attention for vision","author":"Romero","year":"2020"},{"key":"10.1016\/j.engappai.2026.115209_b36","series-title":"International Conference on Artificial Intelligence and Statistics","first-page":"1410","article-title":"Rep the set: Neural networks for learning set representations","author":"Skianis","year":"2020"},{"key":"10.1016\/j.engappai.2026.115209_b37","series-title":"Selfie: Self-supervised pretraining for image embedding","author":"Trinh","year":"2019"},{"issue":"151","key":"10.1016\/j.engappai.2026.115209_b38","first-page":"1","article-title":"Universal approximation of functions on sets","volume":"23","author":"Wagstaff","year":"2022","journal-title":"J. Mach. Learn. Res."},{"issue":"7","key":"10.1016\/j.engappai.2026.115209_b39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3465401","article-title":"A survey on session-based recommender systems","volume":"54","author":"Wang","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.engappai.2026.115209_b40","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A., 2015. Unsupervised learning of visual representations using videos. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2794\u20132802.","DOI":"10.1109\/ICCV.2015.320"},{"issue":"375","key":"10.1016\/j.engappai.2026.115209_b41","first-page":"1","article-title":"Set-valued classification with out-of-distribution detection for many classes","volume":"24","author":"Wang","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2026.115209_b42","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.inffus.2020.10.002","article-title":"Bridging deep and multiple kernel learning: A review","volume":"67","author":"Wang","year":"2021","journal-title":"Inf. Fusion"},{"issue":"1","key":"10.1016\/j.engappai.2026.115209_b43","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/s11263-019-01217-w","article-title":"Robust attentional aggregation of deep feature sets for multi-view 3D reconstruction","volume":"128","author":"Yang","year":"2020","journal-title":"Int. J. Comput. Vis."},{"issue":"1","key":"10.1016\/j.engappai.2026.115209_b44","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1109\/TKDE.2023.3282907","article-title":"Self-supervised learning for recommender systems: A survey","volume":"36","author":"Yu","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.engappai.2026.115209_b45","article-title":"Deep sets","volume":"30","author":"Zaheer","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115209_b46","series-title":"ERNIE: Enhanced language representation with informative entities","author":"Zhang","year":"2019"},{"key":"10.1016\/j.engappai.2026.115209_b47","series-title":"Fspool: Learning set representations with featurewise sort pooling","author":"Zhang","year":"2019"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626014934?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626014934?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T06:48:59Z","timestamp":1781592539000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626014934"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":47,"alternative-id":["S0952197626014934"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115209","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Learning set representations with self-supervised masked transformer","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115209","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115209"}}