{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T21:05:23Z","timestamp":1790111123900,"version":"4.0.1"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109378","type":"journal-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T14:57:50Z","timestamp":1783781870000},"page":"109378","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["A unified basis decomposition framework for addressing the federated learning trilemma: Communication-efficiency, personalization, and privacy"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5912-4716","authenticated-orcid":false,"given":"Zhaoyang","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juncheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0991-1970","authenticated-orcid":false,"given":"Yao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7317-8059","authenticated-orcid":false,"given":"Xin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5143-3645","authenticated-orcid":false,"given":"Youfang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1017-2231","authenticated-orcid":false,"given":"Jing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109378_bib0001","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume":"30","author":"Alistarh","year":"2017","journal-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA, December 4-9"},{"key":"10.1016\/j.neunet.2026.109378_bib0002","series-title":"Proceedings of the 35th international conference on machine learning (ICML), stockholmsm\u00e4ssan, stockholm, sweden, july 10-15","first-page":"560","article-title":"SignSGD: Compressed optimisation for non-convex problems","author":"Bernstein","year":"2018"},{"key":"10.1016\/j.neunet.2026.109378_bib0003","series-title":"Proceedings of ACM SIGKDD international conference on knowledge discovery and data mining (SIGKDD), san francisco, CA, USA, august 26-29","first-page":"245","article-title":"Random projection in dimensionality reduction: applications to image and text data","author":"Bingham","year":"2001"},{"key":"10.1016\/j.neunet.2026.109378_bib0004","unstructured":"Canziani, A., Paszke, A., & Culurciello, E. (2016). An analysis of deep neural network models for practical applications. arXiv preprint arXiv: 1605.07678."},{"issue":"11","key":"10.1016\/j.neunet.2026.109378_bib0005","doi-asserted-by":"crossref","first-page":"16671","DOI":"10.1109\/TNNLS.2023.3297103","article-title":"Metafed: Federated learning among federations with cyclic knowledge distillation for personalized healthcare","volume":"35","author":"Chen","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109378_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106409","article-title":"Federated learning using model projection for multi-center disease diagnosis with non-IID data","volume":"178","author":"Du","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109378_bib0007","first-page":"16937","article-title":"Inverting gradients-how easy is it to break privacy in federated learning?","volume":"33","author":"Geiping","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems (NeurIPS), virtual, December 6-12"},{"key":"10.1016\/j.neunet.2026.109378_bib0008","series-title":"Foundations of cryptography, volume 2","author":"Goldreich","year":"2004"},{"key":"10.1016\/j.neunet.2026.109378_bib0009","series-title":"Matrix computations","author":"Golub","year":"2013"},{"key":"10.1016\/j.neunet.2026.109378_bib0010","series-title":"Proceedings of international joint conference on artificial intelligence, (IJCAI), jeju, south korea, august 3-9","first-page":"4147","article-title":"Practical hybrid gradient compression for federated learning systems","author":"Hu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109378_bib0011","series-title":"Proceedings of the ACM on web conference (WWW), sydney, australia, april 28-may 2","first-page":"807","article-title":"FedRIR: Rethinking information representation in federated learning","author":"Huang","year":"2025"},{"issue":"6","key":"10.1016\/j.neunet.2026.109378_bib0012","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1038\/s42256-020-0186-1","article-title":"Secure, privacy-preserving and federated machine learning in medical imaging","volume":"2","author":"Kaissis","year":"2020","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109378_bib0013","series-title":"IEEE\/CVF Conference on computer vision and pattern recognition (cvpr), seattle, wa, usa, june 16-22","first-page":"12385","article-title":"Communication-efficient federated learning with accelerated client gradient","author":"Kim","year":"2024"},{"issue":"11","key":"10.1016\/j.neunet.2026.109378_bib0014","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":"Proceedings of the IEEE"},{"key":"10.1016\/j.neunet.2026.109378_bib0015","series-title":"International conference on learning representations (ICLR), vancouver, BC, canada, april 30, - may 3","article-title":"Measuring the intrinsic dimension of objective landscapes","author":"Li","year":"2018"},{"key":"10.1016\/j.neunet.2026.109378_bib0016","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020","journal-title":"Proceedings of Conference on Machine Learning and Systems (MLSys), Austin, TX, USA, March 2-4"},{"key":"10.1016\/j.neunet.2026.109378_bib0017","series-title":"International conference on learning representations (ICLR), virtual event, austria, may 3-7","article-title":"FedBN: Federated learning on non-IID features via local batch normalization","author":"Li","year":"2021"},{"key":"10.1016\/j.neunet.2026.109378_bib0018","series-title":"International conference on learning representations (ICLR),toulon, france, april 24-26","article-title":"Revisiting batch normalization for practical domain adaptation","author":"Li","year":"2017"},{"key":"10.1016\/j.neunet.2026.109378_bib0019","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Medical Image Analysis"},{"issue":"06","key":"10.1016\/j.neunet.2026.109378_bib0020","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1109\/TBDATA.2022.3177197","article-title":"Personalized federated learning with adaptive batchnorm for healthcare","volume":"10","author":"Lu","year":"2024","journal-title":"IEEE Transactions on Big Data"},{"key":"10.1016\/j.neunet.2026.109378_bib0021","doi-asserted-by":"crossref","first-page":"5065","DOI":"10.1109\/TMM.2023.3330091","article-title":"FedSH: Towards privacy-preserving text-based person re-identification","volume":"26","author":"Ma","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"issue":"12","key":"10.1016\/j.neunet.2026.109378_bib0022","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2310002121","article-title":"The training process of many deep networks explores the same low-dimensional manifold","volume":"121","author":"Mao","year":"2024","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"10.1016\/j.neunet.2026.109378_bib0023","series-title":"Proceedings of the 20th international conference on artificial intelligence and statistics (aistats), fort lauderdale, fl, USA, 20-22 april","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume":"vol. 54","author":"McMahan","year":"2017"},{"issue":"9","key":"10.1016\/j.neunet.2026.109378_bib0024","doi-asserted-by":"crossref","first-page":"2093","DOI":"10.1109\/TMM.2017.2729400","article-title":"Retrieval from and understanding of large-scale multi-modal medical datasets: A review","volume":"19","author":"M\u00fcller","year":"2017","journal-title":"IEEE Transactions on Multimedia"},{"issue":"18","key":"10.1016\/j.neunet.2026.109378_bib0025","doi-asserted-by":"crossref","first-page":"2164","DOI":"10.1001\/jama.298.18.2164","article-title":"Influence of the HIPAA privacy rule on health research","volume":"298","author":"Ness","year":"2007","journal-title":"Jama"},{"issue":"9","key":"10.1016\/j.neunet.2026.109378_bib0026","doi-asserted-by":"crossref","first-page":"3400","DOI":"10.1109\/TNNLS.2019.2944481","article-title":"Robust and communication-efficient federated learning from non-IID data","volume":"31","author":"Sattler","year":"2019","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109378_bib0027","doi-asserted-by":"crossref","first-page":"19304","DOI":"10.52202\/068431-1403","article-title":"Diagnosing failures of fairness transfer across distribution shift in real-world medical settings","volume":"35","author":"Schrouff","year":"2022","journal-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA, November 28, - December 9"},{"key":"10.1016\/j.neunet.2026.109378_bib0028","doi-asserted-by":"crossref","first-page":"1379","DOI":"10.1109\/TSP.2023.3265886","article-title":"Communication-efficient federated linear and deep generalized canonical correlation analysis","volume":"71","author":"Shrestha","year":"2023","journal-title":"IEEE Transactions on Signal Processing"},{"key":"10.1016\/j.neunet.2026.109378_bib0029","series-title":"Introduction to linear algebra","author":"Strang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109378_bib0030","series-title":"Proceedings of the conference on empirical methods in natural language processing (EMNLP), online, november 16-20","first-page":"2118","article-title":"Feded: Federated learning via ensemble distillation for medical relation extraction","author":"Sui","year":"2020"},{"key":"10.1016\/j.neunet.2026.109378_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.cose.2021.102402","article-title":"Privacy preservation in federated learning: An insightful survey from the GDPR perspective","volume":"110","author":"Truong","year":"2021","journal-title":"Computers & Security"},{"key":"10.1016\/j.neunet.2026.109378_bib0032","series-title":"IEEE International conference on acoustics, speech and signal processing (icassp), seoul, republic of korea, april 14-19","first-page":"5805","article-title":"Communication-efficient federated learning through adaptive weight clustering and server-side distillation","author":"Tsouvalas","year":"2024"},{"key":"10.1016\/j.neunet.2026.109378_bib0033","article-title":"Towards personalized federated learning via heterogeneous model reassembly","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA, December 10, - 16"},{"issue":"3","key":"10.1016\/j.neunet.2026.109378_bib0034","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1111\/jrh.12177","article-title":"What can the national broadband map tell us about the health care connectivity gap?","volume":"33","author":"Whitacre","year":"2017","journal-title":"The Journal of Rural Health"},{"key":"10.1016\/j.neunet.2026.109378_bib0035","article-title":"Fedcache: A knowledge cache-driven federated learning architecture for personalized edge intelligence","author":"Wu","year":"2024","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"10.1016\/j.neunet.2026.109378_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106754","article-title":"Federated learning via multi-attention guided UNet for thyroid nodule segmentation of ultrasound images","volume":"181","author":"Xiang","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109378_bib0037","doi-asserted-by":"crossref","first-page":"2172","DOI":"10.1109\/TSP.2023.3284381","article-title":"Riemannian low-rank model compression for federated learning with over-the-air aggregation","volume":"71","author":"Xue","year":"2023","journal-title":"IEEE Transactions on Signal Processing"},{"key":"10.1016\/j.neunet.2026.109378_bib0038","series-title":"IEEE International symposium on biomedical imaging (isbi), nice, france, april 13-16","first-page":"191","article-title":"Medmnist classification decathlon: A lightweight automl benchmark for medical image analysis","author":"Yang","year":"2021"},{"issue":"1","key":"10.1016\/j.neunet.2026.109378_bib0039","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s11633-022-1343-2","article-title":"Federated learning with privacy-preserving and model IP-right-protection","volume":"20","author":"Yang","year":"2023","journal-title":"Machine Intelligence Research"},{"key":"10.1016\/j.neunet.2026.109378_bib0040","series-title":"Proceedings of the 36th international conference on machine learning (icml), long beach, california, USA, 9-15 june","first-page":"7252","article-title":"Bayesian nonparametric federated learning of neural networks","author":"Yurochkin","year":"2019"},{"issue":"1","key":"10.1016\/j.neunet.2026.109378_bib0041","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3389685","article-title":"The effect of the GDPR on privacy policies: Recent progress and future promise","volume":"12","author":"Zaeem","year":"2020","journal-title":"ACM Transactions on Management Information Systems"},{"key":"10.1016\/j.neunet.2026.109378_bib0042","series-title":"European conference on computer vision (ECCV), zurich, switzerland, september 6-12","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"Zeiler","year":"2014"},{"key":"10.1016\/j.neunet.2026.109378_bib0043","series-title":"Advances in neural information processing systems 36: Annual conference on neural information processing systems (neurIPS), new orleans, LA, USA, december 10, - 16","article-title":"Eliminating domain bias for federated learning in representation space","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109378_bib0044","series-title":"Association for the advancement of artificial intelligence (AAAI), washington, DC, USA, february 7-14","first-page":"11237","article-title":"FedALA: Adaptive local aggregation for personalized federated learning","volume":"vol. 37","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109378_bib0045","article-title":"Knowledge-distillation based personalized federated learning with distribution constraints","author":"Zhang","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109378_bib0046","unstructured":"Zhao, B., Mopuri, K. R., & Bilen, H. (2020). IDLG: Improved deep leakage from gradients. arXiv preprint arXiv: 2001.02610."},{"key":"10.1016\/j.neunet.2026.109378_bib0047","article-title":"E-3SFC: Communication-efficient federated learning with double-way features synthesizing","author":"Zhou","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109378_bib0048","article-title":"Deep leakage from gradients","volume":"32","author":"Zhu","year":"2019","journal-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, BC, Canada, December 8-14, 2019"},{"issue":"7","key":"10.1016\/j.neunet.2026.109378_bib0049","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1145\/3657301","article-title":"A survey of trustworthy representation learning across domains","volume":"18","author":"Zhu","year":"2024","journal-title":"ACM Transactions on Knowledge Discovery from Data"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026008361?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026008361?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T20:11:27Z","timestamp":1790107887000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026008361"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":49,"alternative-id":["S0893608026008361"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109378","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A unified basis decomposition framework for addressing the federated learning trilemma: Communication-efficiency, personalization, and privacy","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109378","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":"109378"}}