{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T17:30:36Z","timestamp":1773423036684,"version":"3.50.1"},"reference-count":232,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tkde.2025.3555328","type":"journal-article","created":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T04:22:30Z","timestamp":1743222150000},"page":"1-20","source":"Crossref","is-referenced-by-count":19,"title":["Ten Challenging Problems in Federated Foundation Models"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3040-6140","authenticated-orcid":false,"given":"Tao","family":"Fan","sequence":"first","affiliation":[{"name":"WeBank, Shenzhen, China"}]},{"given":"Hanlin","family":"Gu","sequence":"additional","affiliation":[{"name":"WeBank, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9083-8998","authenticated-orcid":false,"given":"Xuemei","family":"Cao","sequence":"additional","affiliation":[{"name":"Southwestern University of Finance and Economic, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7677-2865","authenticated-orcid":false,"given":"Chee Seng","family":"Chan","sequence":"additional","affiliation":[{"name":"Universiti Malaya, Malaysia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2579-4380","authenticated-orcid":false,"given":"Qian","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8407-0780","authenticated-orcid":false,"given":"Yiqiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7853-9508","authenticated-orcid":false,"given":"Yihui","family":"Feng","sequence":"additional","affiliation":[{"name":"Southwestern University of Finance and Economic, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8572-2907","authenticated-orcid":false,"given":"Yang","family":"Gu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, China"}]},{"given":"Jiaxiang","family":"Geng","sequence":"additional","affiliation":[{"name":"Duke Kunshan University, Kunshan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3664-5009","authenticated-orcid":false,"given":"Bing","family":"Luo","sequence":"additional","affiliation":[{"name":"Duke Kunshan University, Kunshan, China"}]},{"given":"Shuoling","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Innovation, E Fund Management Co., Ltd., China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8403-8211","authenticated-orcid":false,"given":"Win Kent","family":"Ong","sequence":"additional","affiliation":[{"name":"Universiti Malaya, Malaysia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9096-8792","authenticated-orcid":false,"given":"Chao","family":"Ren","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Sweden"}]},{"given":"Jiaqi","family":"Shao","sequence":"additional","affiliation":[{"name":"Duke Kunshan University, Kunshan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5512-687X","authenticated-orcid":false,"given":"Chuan","family":"Sun","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1967-2953","authenticated-orcid":false,"given":"Xiaoli","family":"Tang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"given":"Hong Xi","family":"Tae","sequence":"additional","affiliation":[{"name":"Universiti Malaya, Malaysia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5598-0312","authenticated-orcid":false,"given":"Yongxin","family":"Tong","sequence":"additional","affiliation":[{"name":"Beihang University, China"}]},{"given":"Shuyue","family":"Wei","sequence":"additional","affiliation":[{"name":"Beihang University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0965-9058","authenticated-orcid":false,"given":"Fan","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9348-2982","authenticated-orcid":false,"given":"Wei","family":"Xi","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, China"}]},{"given":"Mingcong","family":"Xu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0604-8120","authenticated-orcid":false,"given":"He","family":"Yang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0406-6774","authenticated-orcid":false,"given":"Xin","family":"Yang","sequence":"additional","affiliation":[{"name":"Southwestern University of Finance and Economic, China"}]},{"given":"Jiangpeng","family":"Yan","sequence":"additional","affiliation":[{"name":"Institute of Innovation, E Fund Management Co., Ltd., China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0705-4756","authenticated-orcid":false,"given":"Hao","family":"Yu","sequence":"additional","affiliation":[{"name":"Southwestern University of Finance and Economic, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6893-8650","authenticated-orcid":false,"given":"Han","family":"Yu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1870-1051","authenticated-orcid":false,"given":"Teng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, China"}]},{"given":"Yifei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9065-6852","authenticated-orcid":false,"given":"Xiaojin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3447-5349","authenticated-orcid":false,"given":"Zhenzhe","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8162-7096","authenticated-orcid":false,"given":"Lixin","family":"Fan","sequence":"additional","affiliation":[{"name":"Principal Scientist of Artificial Intelligence at WeBank, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5059-8360","authenticated-orcid":false,"given":"Qiang","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02443-6"},{"key":"ref2","article-title":"FATE-LLM: A industrial grade federated learning framework for LLMs","author":"Fan","year":"2023"},{"key":"ref3","article-title":"Grounding foundation models through federated transfer learning: A general framework","author":"Kang","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2025.3552524"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2025.104293"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.976"},{"key":"ref8","first-page":"1","article-title":"Privately customizing prefinetuning to better match user data in federated learning","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Hou"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671573"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671897"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447454"},{"key":"ref12","article-title":"FLoRA: Federated fine-tuning LLMs with heterogeneous low-rank adaptations","author":"Wang","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583518"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01755"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-82240-7_8"},{"key":"ref16","article-title":"Federated full-parameter tuning of billion-sized language models with communication cost","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qin"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.464"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3641512.3690630"},{"key":"ref19","article-title":"FedPIT: Towards privacy-preserving and few-shot federated instruction tuning","author":"Zhang","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671582"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-024-3639-x"},{"key":"ref22","article-title":"Enhancing storage and computational efficiency in federated multimodal learning for large-scale models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01218"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3436874"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681384"},{"key":"ref26","first-page":"303","article-title":"Diffusion-driven data replay: A novel approach to combat forgetting in federated class CL","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Liang"},{"key":"ref27","first-page":"12073","article-title":"Federated continual learning with weighted inter-client transfer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yoon"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00992"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/303"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-05933-9_47"},{"key":"ref31","article-title":"Federated continual learning via prompt-based dual knowledge transfer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Piao"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671948"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512222"},{"key":"ref34","article-title":"Unlearning via sparse representations","author":"Shah","year":"2023"},{"key":"ref35","article-title":"A few-shot label unlearning in vertical federated learning","author":"Gu","year":"2024"},{"key":"ref36","first-page":"24150","article-title":"Ferrari: Federated feature unlearning via optimizing feature sensitivity","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/446"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796721"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229075"},{"key":"ref40","first-page":"3457","article-title":"SIFU: Sequential informed federated unlearning for efficient and provable client unlearning in federated optimization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Fraboni"},{"key":"ref41","first-page":"1","article-title":"Federated unlearning: How to efficiently erase a client in federated learning?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Halimi"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.2200198"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2024.3382321"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179336"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3297905"},{"key":"ref46","article-title":"Federated unlearning: A perspective of stability and fairness","author":"Shao","year":"2024"},{"key":"ref47","article-title":"FedBaF: Federated learning aggregation biased by a foundation model","author":"Park","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA61862.2024.00228"},{"key":"ref49","first-page":"39409","article-title":"Dual-personalizing adapter for federated foundation models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.14778\/3617838.3617842"},{"key":"ref51","article-title":"Beyond the federation: Topology-aware federated learning for generalization to unseen clients","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ma"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3164914"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3430819"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00177"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"ref56","first-page":"1","article-title":"Explanations from LLMs make small reasoners better","volume-title":"Proc. Sustain. AI Workshop","author":"Li"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.189"},{"key":"ref58","article-title":"PDSS: A privacy-preserving framework for step-by-step distillation of LLMs","author":"Fan","year":"2024"},{"key":"ref59","article-title":"Federated domain-specific knowledge transfer on LLMs using synthetic data","author":"Li","year":"2024"},{"key":"ref60","article-title":"A split-and-privatize framework for large language model fine-tuning","author":"Shen","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3359789.3359824"},{"key":"ref62","first-page":"1","article-title":"MiniLLM: Knowledge distillation of LLMs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu"},{"key":"ref63","first-page":"1","article-title":"Multimodal federated learning via contrastive representation ensemble","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref64","first-page":"243","article-title":"FedMKT: Federated mutual knowledge transfer for large and small language models","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Fan"},{"key":"ref65","article-title":"GPT-FL: Generative pre-trained model-assisted federated learning","author":"Zhang","year":"2023"},{"key":"ref66","article-title":"Offsite-tuning: Transfer learning without full model","author":"Xiao","year":"2023"},{"key":"ref67","article-title":"FedCoLLM: A parameter-efficient federated co-tuning framework for large and small language models","author":"Fan","year":"2024"},{"key":"ref68","article-title":"Mutual enhancement of large and small language models with cross-silo knowledge transfer","author":"Deng","year":"2023"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2940820"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016304"},{"key":"ref71","article-title":"FedCCEA: A practical approach of client contribution evaluation for federated learning","author":"Shyn","year":"2021"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00073"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006327"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_10"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00228"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i6.16721"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/LNET.2019.2947144"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2971981"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900649"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS57875.2023.00027"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322475"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2991725"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3388831.3388843"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2020.07.045"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00064"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/474"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/552"},{"key":"ref88","article-title":"Multi-session budget optimization for forward auction-based federated learning","author":"Tang","year":"2023"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3474102"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/912"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/972"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195956"},{"key":"ref93","article-title":"FedSOV: Federated model secure ownership verification with unforgeable signature","author":"Yang","year":"2023"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2024.3390761"},{"key":"ref95","article-title":"FedCIP: Federated client intellectual property protection with traitor tracking","author":"Liang","year":"2023"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/srds53918.2021.00038"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/SMC52423.2021.9658998"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3630636"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13214306"},{"key":"ref100","article-title":"Federated data-efficient instruction tuning for LLMs","author":"Qin","year":"2024"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-38916-x"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-024-06162-1"},{"key":"ref103","article-title":"FedMD: Heterogenous federated learning via model distillation","author":"Li","year":"2019"},{"key":"ref104","article-title":"DynaBERT: Dynamic BERT with adaptive width and depth","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hou"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651384"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488756"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.01.046"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/3563219"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3363240"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1145\/3679014"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/3656049"},{"key":"ref112","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref113","article-title":"Federated large language model: A position paper","author":"Chen","year":"2023","journal-title":"arXiv.2307.08925"},{"key":"ref114","article-title":"Position paper: Assessing robustness, privacy, and fairness in federated learning integrated with foundation models","author":"Li","year":"2024"},{"key":"ref115","article-title":"When foundation model meets federated learning: Motivations, challenges, and future directions","author":"Zhuang","year":"2023"},{"key":"ref116","first-page":"7174","article-title":"Federated foundation models: Privacy-preserving and collaborative learning for large models","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Yu"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/919"},{"key":"ref118","article-title":"Synergizing foundation models and federated learning: A survey","author":"Li","year":"2024"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1145\/3701039"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.303"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.59"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/infocom52122.2024.10621164"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5569-1_17"},{"key":"ref124","first-page":"30590","article-title":"Federated learning from vision-language foundation models: Theoretical analysis and method","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref125","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref126","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref127","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Int. Conf. Mach. Learn. Syst.","author":"Li"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02576"},{"key":"ref129","article-title":"Towards federated foundation models: Scalable dataset pipelines for group-structured learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Charles"},{"key":"ref130","article-title":"Enhancing data quality in federated fine-tuning of foundation models","author":"Zhao","year":"2024"},{"key":"ref131","article-title":"FedBPT: Efficient federated black-box prompt tuning for LLMs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref132","first-page":"1605","article-title":"Local model poisoning attacks to byzantine-robust federated learning","volume-title":"Proc. 29th USENIX Conf. Secur. Symp.","author":"Fang"},{"key":"ref133","article-title":"Attack of the tails: Yes, you really can backdoor federated learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671545"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3352415"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72111-3_27"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS61880.2024.10620662"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1007\/s41666-020-00082-4"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-82240-7_2"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3429383"},{"issue":"1","key":"ref143","article-title":"Federated continual learning for edge-AI: A comprehensive survey","volume":"1","author":"Wang","year":"2024","journal-title":"ACM Comput. Surveys"},{"key":"ref144","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71782-7_35"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1145\/3510032"},{"key":"ref148","first-page":"1","article-title":"Quantifying memorization across neural language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Carlini"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2014.2320500"},{"key":"ref150","first-page":"677","article-title":"Transfer learning via dimensionality reduction","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Pan"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3194884"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1145\/3488932.3517406"},{"key":"ref153","first-page":"2535","article-title":"On the power of curriculum learning in training deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hacohen"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-022-00894-4"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1017\/9781139061773"},{"key":"ref156","article-title":"Federated graph learning\u2013A position paper","author":"Zhang","year":"2021"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1145\/3575637.3575644"},{"key":"ref158","first-page":"1396","article-title":"Personalized subgraph federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baek"},{"key":"ref159","article-title":"GraphFM: A scalable framework for multi-graph pretraining","author":"Lachi","year":"2024"},{"key":"ref160","article-title":"NetSafe: Exploring the topological safety of multi-agent networks","author":"Yu","year":"2024"},{"key":"ref161","article-title":"GraphRouter: A graph-based router for LLM selections","author":"Feng","year":"2024"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29007"},{"key":"ref163","article-title":"Towards federated foundation models: Scalable dataset pipelines for group-structured learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Charles"},{"key":"ref164","article-title":"Selective pre-training for private fine-tuning","author":"Yu","year":"2023"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1007\/11787006_1"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1145\/1536414.1536440"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1986.25"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21505"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881970-018"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1137\/0117107"},{"key":"ref171","article-title":"Incentive allocation in vertical federated learning based on bankruptcy problem","author":"Khan","year":"2023"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_8"},{"key":"ref173","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref174","article-title":"Rewarding high-quality data via influence functions","author":"Richardson","year":"2019"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/iThings\/GreenCom\/CPSCom\/SmartData.2019.00148"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1063\/1.3511332"},{"key":"ref177","article-title":"When crowdsensing meets federated learning: Privacy-preserving mobile crowdsensing system","author":"Zhao","year":"2021"},{"key":"ref178","first-page":"16937","article-title":"Inverting gradients-how easy is it to break privacy in federated learning?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Geiping"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737416"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3182979"},{"key":"ref181","first-page":"374","article-title":"Towards federated learning at scale: System design","volume-title":"Proc. 2nd Conf. Mach. Learn. Syst.","author":"Bonawitz"},{"key":"ref182","first-page":"2938","article-title":"How to backdoor federated learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Bagdasaryan"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00065"},{"key":"ref184","first-page":"14747","article-title":"Deep leakage from gradients","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref185","first-page":"5636","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yin"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2967772"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3379659"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3041854"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2017.2701817"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.007.2400133"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1145\/3460771"},{"key":"ref192","first-page":"119","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Blanchard"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.2987774"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1145\/3701741"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3379933"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1016\/j.jik.2024.100601"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3078974"},{"key":"ref198","article-title":"DeepMarks: A digital fingerprinting framework for deep neural networks","author":"Chen","year":"2018"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304051"},{"key":"ref200","first-page":"4716","article-title":"Rethinking deep neural network ownership verification: Embedding passports to defeat ambiguity attacks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088846"},{"key":"ref202","first-page":"1615","article-title":"Turning your weakness into a strength: Watermarking deep neural networks by backdooring","volume-title":"Proc. 27th USENIX Secur. Symp.","author":"Adi"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1145\/3196494.3196550"},{"key":"ref204","article-title":"Who leaked the model? Tracking IP infringers in accountable federated learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Yu","year":"2023"},{"key":"ref205","article-title":"Performance-lossless black-box model watermarking","author":"Zhao","year":"2023"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26750"},{"key":"ref207","first-page":"1","article-title":"Privacy backdoors: Enhancing membership inference through poisoning pre-trained models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3166101"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10787"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging8060152"},{"key":"ref211","article-title":"Watermarking vision-language pre-trained models for multi-modal embedding as a service","author":"Tang","year":"2023"},{"key":"ref212","article-title":"Federated LLMs: Current progress and future directions","author":"Yao","year":"2024"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3235443"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1145\/3659205"},{"key":"ref215","first-page":"25438","article-title":"NLP from scratch without large-scale pretraining: A simple and efficient framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yao"},{"key":"ref216","article-title":"Improving multimodal reasoning in LLMs via federated example selection","author":"Fawcett","year":"2024"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.488"},{"key":"ref218","article-title":"Learning to compress prompts with gist tokens","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mu"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-71467-2_1"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1145\/3510587"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02601"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01306"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3690668"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488679"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796935"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3316421"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110844"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3146448"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3253718"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26023"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3131040"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/4358933\/10944288.pdf?arnumber=10944288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T04:19:55Z","timestamp":1749183595000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10944288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":232,"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3555328","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}