{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T14:01:51Z","timestamp":1785074511012,"version":"3.55.0"},"reference-count":70,"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\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22DZ1100102"],"award-info":[{"award-number":["22DZ1100102"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100031931","name":"Shanghai Artificial Intelligence Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100031931","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0160201"],"award-info":[{"award-number":["2022ZD0160201"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.knosys.2026.116441","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T06:25:04Z","timestamp":1781763904000},"page":"116441","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Mosaic: Data-free knowledge distillation via mixture-of-experts for heterogeneous distributed environments"],"prefix":"10.1016","volume":"349","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9131-3245","authenticated-orcid":false,"given":"Junming","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanting","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyuan","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aoqi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yirong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ding","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5048-0319","authenticated-orcid":false,"given":"Shiping","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116441_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113503","article-title":"A comprehensive survey on integrating large language models with knowledge-based methods","volume":"318","author":"Yang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116441_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.115641","article-title":"Deep structure alignment network for scalable unsupervised domain adaptation","volume":"340","author":"Wang","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116441_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.115901","article-title":"Geometry-guided multi-view 3D object detection for autonomous driving","volume":"342","author":"Pan","year":"2026","journal-title":"Knowl.-Based Syst."},{"issue":"5","key":"10.1016\/j.knosys.2026.116441_b4","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1109\/JIOT.2016.2579198","article-title":"Edge computing: Vision and challenges","volume":"3","author":"Shi","year":"2016","journal-title":"IEEE Internet Things J."},{"issue":"3","key":"10.1016\/j.knosys.2026.116441_b5","doi-asserted-by":"crossref","first-page":"2596","DOI":"10.1109\/TETCI.2025.3621221","article-title":"Efficient medical image segmentation via reinforcement learning-driven K-space sampling","volume":"10","author":"Li","year":"2026","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"10.1016\/j.knosys.2026.116441_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.115819","article-title":"Rethinking sparse supervision on federated long-tailed learning","volume":"342","author":"Zhou","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116441_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.115421","article-title":"Decoupling and alleviating knowledge bias for federated learning under data heterogeneity","volume":"337","author":"Li","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116441_b8","series-title":"FedKD-hybrid: Federated hybrid knowledge distillation for lithography hotspot detection","author":"Li","year":"2025"},{"key":"10.1016\/j.knosys.2026.116441_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.115210","article-title":"A scalable unsupervised framework for multi-aspect labeling of multilingual and multi-domain review data","volume":"335","author":"Park","year":"2026","journal-title":"Knowl.-Based Syst."},{"issue":"9","key":"10.1016\/j.knosys.2026.116441_b10","doi-asserted-by":"crossref","first-page":"15643","DOI":"10.1109\/TNNLS.2025.3563537","article-title":"Threats and defenses in the federated learning life cycle: A comprehensive survey and challenges","volume":"36","author":"Li","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116441_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.115335","article-title":"FedAATKE: Adaptive aggregation and targeted knowledge exchange for communication-efficient personalized federated learning","volume":"336","author":"Zhang","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116441_b12","series-title":"Proceedings of the 37th International Conference on Machine Learning","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume":"119","author":"Karimireddy","year":"2020"},{"key":"10.1016\/j.knosys.2026.116441_b13","series-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics","first-page":"1273","article-title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","volume":"vol. 54","author":"McMahan","year":"2017"},{"key":"10.1016\/j.knosys.2026.116441_b14","series-title":"Fednlp: Benchmarking federated learning methods for natural language processing tasks","author":"Lin","year":"2021"},{"key":"10.1016\/j.knosys.2026.116441_b15","series-title":"International Conference on Learning Representations","article-title":"Hetero{fl}: Computation and communication efficient federated learning for heterogeneous clients","author":"Diao","year":"2021"},{"issue":"24","key":"10.1016\/j.knosys.2026.116441_b16","doi-asserted-by":"crossref","first-page":"21811","DOI":"10.1109\/JIOT.2023.3299573","article-title":"Client selection in federated learning: Principles, challenges, and opportunities","volume":"10","author":"Fu","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.knosys.2026.116441_b17","series-title":"Advances in Neural Information Processing Systems","first-page":"29677","article-title":"FedRolex: Model-heterogeneous federated learning with rolling sub-model extraction","volume":"vol. 35","author":"Alam","year":"2022"},{"key":"10.1016\/j.knosys.2026.116441_b18","series-title":"Advances in Neural Information Processing Systems","first-page":"17854","article-title":"DFRD: Data-free robustness distillation for heterogeneous federated learning","volume":"vol. 36","author":"Luo","year":"2023"},{"key":"10.1016\/j.knosys.2026.116441_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.115276","article-title":"Prototype-guided cyclic federated learning with knowledge distillation","volume":"336","author":"Meng","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116441_b20","series-title":"ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1601","article-title":"Learnable instance attention filtering for adaptive detector distillation","author":"Liu","year":"2026"},{"key":"10.1016\/j.knosys.2026.116441_b21","series-title":"FedMD: Heterogeneous federated learning via model distillation","author":"Li","year":"2019"},{"key":"10.1016\/j.knosys.2026.116441_b22","series-title":"2022 IEEE International Conference on Multimedia and Expo","first-page":"1","article-title":"FEDIC: Federated learning on non-IID and long-tailed data via calibrated distillation","author":"Shang","year":"2022"},{"key":"10.1016\/j.knosys.2026.116441_b23","doi-asserted-by":"crossref","unstructured":"Y. Li, C. Yang, H. Zeng, Z. Dong, Z. An, Y. Xu, Y. Tian, H. Wu, Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2025, pp. 7262\u20137272.","DOI":"10.1109\/ICCV51701.2025.00682"},{"key":"10.1016\/j.knosys.2026.116441_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.116359","article-title":"FedSGK: Data-free subgraph federated distillation with a public embedding proxy for triple heterogeneity","volume":"348","author":"Tang","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116441_b25","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"12878","article-title":"Data-free knowledge distillation for heterogeneous federated learning","volume":"139","author":"Zhu","year":"2021"},{"key":"10.1016\/j.knosys.2026.116441_b26","first-page":"1","article-title":"Data-free knowledge filtering and distillation in federated learning","author":"Lu","year":"2024","journal-title":"IEEE Trans. Big Data"},{"key":"10.1016\/j.knosys.2026.116441_b27","series-title":"Advances in Neural Information Processing Systems","first-page":"21414","article-title":"DENSE: Data-free one-shot federated learning","volume":"vol. 35","author":"Zhang","year":"2022"},{"key":"10.1016\/j.knosys.2026.116441_b28","doi-asserted-by":"crossref","unstructured":"L. Zhang, L. Shen, L. Ding, D. Tao, L.-Y. Duan, Fine-Tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 10174\u201310183.","DOI":"10.1109\/CVPR52688.2022.00993"},{"key":"10.1016\/j.knosys.2026.116441_b29","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"DeGAN : Data-enriching GAN for retrieving representative samples from a trained classifier","author":"Addepalli","year":"2019"},{"key":"10.1016\/j.knosys.2026.116441_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.cose.2023.103319","article-title":"Enhancing federated learning robustness in adversarial environment through clustering non-IID features","volume":"132","author":"Li","year":"2023","journal-title":"Comput. Secur."},{"key":"10.1016\/j.knosys.2026.116441_b31","doi-asserted-by":"crossref","unstructured":"Y. Wang, H. Fu, R. Kanagavelu, Q. Wei, Y. Liu, R.S.M. Goh, An Aggregation-Free Federated Learning for Tackling Data Heterogeneity, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2024, pp. 26233\u201326242.","DOI":"10.1109\/CVPR52733.2024.02478"},{"key":"10.1016\/j.knosys.2026.116441_b32","series-title":"Advances in Neural Information Processing Systems","first-page":"77038","article-title":"Personalized federated learning via feature distribution adaptation","volume":"vol. 37","author":"McLaughlin","year":"2024"},{"issue":"16","key":"10.1016\/j.knosys.2026.116441_b33","first-page":"17395","article-title":"PA3fed: Period-aware adaptive aggregation for improved federated learning","volume":"39","author":"Huang","year":"2025","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116441_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114721","article-title":"MSFGAN: A multi-source federated generative learning paradigm for robust traffic data imputation","volume":"330","author":"Fang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116441_b35","series-title":"The Fourteenth International Conference on Learning Representations","article-title":"Bridging generalization gap of heterogeneous federated clients using generative models","author":"Niu","year":"2026"},{"issue":"2","key":"10.1016\/j.knosys.2026.116441_b36","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1109\/TDSC.2024.3419211","article-title":"FedPA: Generator-based heterogeneous federated prototype adversarial learning","volume":"22","author":"Jiang","year":"2025","journal-title":"IEEE Trans. Dependable Secur. Comput."},{"key":"10.1016\/j.knosys.2026.116441_b37","series-title":"DDTime: Dataset distillation with spectral alignment and information bottleneck for time-series forecasting","author":"Li","year":"2025"},{"key":"10.1016\/j.knosys.2026.116441_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.115304","article-title":"SLATSCOG: A secure authentication framework via federated data generation and temporally-enhanced split learning","volume":"336","author":"Chen","year":"2026","journal-title":"Knowl.-Based Syst."},{"issue":"1","key":"10.1016\/j.knosys.2026.116441_b39","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s13634-021-00767-x","article-title":"Viewpoint robust knowledge distillation for accelerating vehicle re-identification","volume":"2021","author":"Xie","year":"2021","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"10.1016\/j.knosys.2026.116441_b40","doi-asserted-by":"crossref","unstructured":"Q. Lan, Q. Tian, ACAM-KD: Adaptive and Cooperative Attention Masking for Knowledge Distillation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2025, pp. 3957\u20133966.","DOI":"10.1109\/ICCV51701.2025.00377"},{"key":"10.1016\/j.knosys.2026.116441_b41","series-title":"Towards open federated learning platforms: Survey and vision from technical and legal perspectives","author":"Duan","year":"2023"},{"key":"10.1016\/j.knosys.2026.116441_b42","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Data-free one-shot federated learning under very high statistical heterogeneity","author":"Heinbaugh","year":"2023"},{"key":"10.1016\/j.knosys.2026.116441_b43","series-title":"2022 17th Wireless on-Demand Network Systems and Services Conference","first-page":"1","article-title":"Fed2KD: Heterogeneous federated learning for pandemic risk assessment via two-way knowledge distillation","author":"Sun","year":"2022"},{"issue":"5","key":"10.1016\/j.knosys.2026.116441_b44","doi-asserted-by":"crossref","first-page":"5589","DOI":"10.1109\/JIOT.2024.3488565","article-title":"Heterogeneous federated learning via generative model-aided knowledge distillation in the edge","volume":"12","author":"Sun","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.knosys.2026.116441_b45","series-title":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","first-page":"2377","article-title":"Towards the gradient vanishing, divergence mismatching and mode collapse of generative adversarial nets","author":"Zhang","year":"2019"},{"key":"10.1016\/j.knosys.2026.116441_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.115607","article-title":"Noisy or structural? Knowledge graph-based dual-view diffusion for recommendation systems","volume":"339","author":"Li","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116441_b47","series-title":"FedRecon: Missing modality reconstruction in distributed heterogeneous environments","author":"Liu","year":"2025"},{"key":"10.1016\/j.knosys.2026.116441_b48","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8712","article-title":"Dreaming to distill: Data-free knowledge transfer via DeepInversion","author":"Yin","year":"2020"},{"issue":"8","key":"10.1016\/j.knosys.2026.116441_b49","first-page":"8432","article-title":"FedProto: Federated prototype learning across heterogeneous clients","volume":"36","author":"Tan","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116441_b50","series-title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"10.1016\/j.knosys.2026.116441_b51","unstructured":"Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, A.Y. Ng, Reading digits in natural images with unsupervised feature learning, in: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, Granada, Spain, 2011."},{"key":"10.1016\/j.knosys.2026.116441_b52","series-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.knosys.2026.116441_b53","series-title":"Computer Vision \u2013 ECCV 2014","first-page":"446","article-title":"Food-101 \u2013 mining discriminative components with random forests","author":"Bossard","year":"2014"},{"key":"10.1016\/j.knosys.2026.116441_b54","series-title":"Machine Learning Proceedings 1995","first-page":"331","article-title":"NewsWeeder: Learning to filter netnews","author":"Lang","year":"1995"},{"key":"10.1016\/j.knosys.2026.116441_b55","series-title":"Proceedings of the Seventeenth Conference on Computational Natural Language Learning","first-page":"143","article-title":"Towards robust linguistic analysis using OntoNotes","author":"Pradhan","year":"2013"},{"issue":"1","key":"10.1016\/j.knosys.2026.116441_b56","article-title":"CrisisMMD: Multimodal Twitter datasets from natural disasters","volume":"12","author":"Alam","year":"2018","journal-title":"Proc. Int. AAAI Conf. Web Soc. Media"},{"key":"10.1016\/j.knosys.2026.116441_b57","series-title":"Proceedings of Machine Learning and Systems","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020"},{"key":"10.1016\/j.knosys.2026.116441_b58","series-title":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","first-page":"995","article-title":"FedRS: Federated learning with restricted softmax for label distribution non-IID data","author":"Li","year":"2021"},{"key":"10.1016\/j.knosys.2026.116441_b59","series-title":"Adaptive federated optimization","author":"Reddi","year":"2020"},{"key":"10.1016\/j.knosys.2026.116441_b60","series-title":"Advances in Neural Information Processing Systems","first-page":"80543","article-title":"Understanding how consistency works in federated learning via stage-wise relaxed initialization","volume":"vol. 36","author":"Sun","year":"2023"},{"key":"10.1016\/j.knosys.2026.116441_b61","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep Residual Learning for Image Recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.knosys.2026.116441_b62","series-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"10.1016\/j.knosys.2026.116441_b63","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2021.103329","article-title":"Pros and cons of GAN evaluation measures: New developments","volume":"215","author":"Borji","year":"2022","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.knosys.2026.116441_b64","series-title":"International Conference on Learning Representations","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2022"},{"key":"10.1016\/j.knosys.2026.116441_b65","series-title":"2012 IEEE International Conference on Communications","first-page":"917","article-title":"Verifiable symmetric searchable encryption for semi-honest-but-curious cloud servers","author":"Chai","year":"2012"},{"key":"10.1016\/j.knosys.2026.116441_b66","series-title":"2017 IEEE Symposium on Security and Privacy","first-page":"3","article-title":"Membership inference attacks against machine learning models","author":"Shokri","year":"2017"},{"key":"10.1016\/j.knosys.2026.116441_b67","series-title":"2019 IEEE Symposium on Security and Privacy","first-page":"739","article-title":"Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning","author":"Nasr","year":"2019"},{"key":"10.1016\/j.knosys.2026.116441_b68","series-title":"Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security","first-page":"619","article-title":"Property inference attacks on fully connected neural networks using permutation invariant representations","author":"Ganju","year":"2018"},{"key":"10.1016\/j.knosys.2026.116441_b69","series-title":"Advances in Neural Information Processing Systems","first-page":"13294","article-title":"ResShift: Efficient diffusion model for image super-resolution by residual shifting","volume":"vol. 36","author":"Yue","year":"2023"},{"key":"10.1016\/j.knosys.2026.116441_b70","series-title":"Advances in Neural Information Processing Systems","first-page":"42765","article-title":"Taming diffusion prior for image super-resolution with domain shift SDEs","volume":"vol. 37","author":"Cui","year":"2024"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126011676?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126011676?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T13:27:54Z","timestamp":1785072474000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126011676"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":70,"alternative-id":["S0950705126011676"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116441","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Mosaic: Data-free knowledge distillation via mixture-of-experts for heterogeneous distributed environments","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116441","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116441"}}