{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:17:11Z","timestamp":1774023431595,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["JP25K00373"],"award-info":[{"award-number":["JP25K00373"]}]},{"name":"Ongoing Research Funding Program","award":["ORF-2025-102"],"award-info":[{"award-number":["ORF-2025-102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput. Soc. Syst."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tcss.2025.3575623","type":"journal-article","created":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T13:39:41Z","timestamp":1751981981000},"page":"5433-5448","source":"Crossref","is-referenced-by-count":1,"title":["A Robust Aggregation of Federated Large Language Models for Multimodal Knowledge Discovery in Computational Social Systems"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4324-8262","authenticated-orcid":false,"given":"Jinhua","family":"Chen","sequence":"first","affiliation":[{"name":"Graduate School of Science and Engineering, Hosei University, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4385-0975","authenticated-orcid":false,"given":"Chinmay","family":"Chakraborty","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering, Kalinga Institute of Industrial Technology, Bhubaneswar, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4831-7969","authenticated-orcid":false,"given":"Ashok","family":"Polavarapu","sequence":"additional","affiliation":[{"name":"School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0268-0890","authenticated-orcid":false,"given":"Yuning","family":"Qiu","sequence":"additional","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project (AIP), Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4442-3182","authenticated-orcid":false,"given":"Qibin","family":"Zhao","sequence":"additional","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project (AIP), Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6111-8617","authenticated-orcid":false,"given":"Osama","family":"Alfarraj","sequence":"additional","affiliation":[{"name":"Computer Science Department, Community College, King Saud University, Riyadh, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5735-2507","authenticated-orcid":false,"given":"Keping","family":"Yu","sequence":"additional","affiliation":[{"name":"Graduate School of Science and Engineering, Hosei University, Tokyo, Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2024.3476030"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2024.3484460"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2022.3222682"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2023.3298480"},{"key":"ref6","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. 3rd Conf. Mach. Learn. Syst. (MLSys)","author":"Li","year":"2020"},{"key":"ref7","article-title":"Scalable extraction of training data from (production) language models","author":"Nasr","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.98"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671582"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.488"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671897"},{"key":"ref12","first-page":"39879","article-title":"FedDisco: Federated learning with discrepancy-aware collaboration","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ye","year":"2023"},{"key":"ref13","article-title":"Self-driven entropy aggregation for Byzantine-robust heterogeneous federated learning","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Huang","year":"2024"},{"key":"ref14","first-page":"119","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Blanchard","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tsp.2022.3153135"},{"key":"ref16","article-title":"Can you really backdoor federated learning?","author":"Sun","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/sp46214.2022.9833672"},{"key":"ref18","article-title":"Position: Considerations for differentially private learning with large-scale public pretraining","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Tram\u00e8r","year":"2024"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.14722\/ndss.2024.23325","article-title":"Transpose attack: Stealing datasets with bidirectional training","volume-title":"Proc. 31st Annu. Netw. Distrib. Syst. Secur. Symp. (NDSS)","author":"Amit","year":"2024"},{"key":"ref20","article-title":"Privacy leakage on DNNs: A survey of model inversion attacks and defenses","author":"Fang","year":"2024"},{"key":"ref21","article-title":"Balancing similarity and complementarity for federated learning","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Yan","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70694-8_15"},{"key":"ref23","article-title":"Local SGD converges fast and communicates little","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Stich","year":"2019"},{"key":"ref24","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Stat. (AISTATS)","volume":"54","author":"McMahan","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.401"},{"key":"ref26","article-title":"Instruction Tuning with GPT-4","author":"Peng","year":"2023"},{"key":"ref27","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu","year":"2019"},{"key":"ref28","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn. (ICML), Virtual Event","author":"Karimireddy","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26237"},{"key":"ref30","first-page":"100","article-title":"Navigating data heterogeneity in federated learning: A semi-supervised federated object detection","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst. (NeurIPS\u201923)","author":"Kim","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01566"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2451"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599346"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3757"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2024.3452229"},{"key":"ref36","article-title":"Eliminating domain bias for federated learning in representation space","volume-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Zhang","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2298"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2093"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1090"},{"key":"ref40","article-title":"FedRC: Tackling diverse distribution shifts challenge in federated learning by robust clustering","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Guo","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-022-01046-x"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02351"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-industry.60"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.632"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.488"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3698856"},{"key":"ref47","article-title":"PrE-Text: Training language models on private federated data in the age of LLMs","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Hou","year":"2024"},{"key":"ref48","first-page":"69069","article-title":"Thinking forward: Memory-efficient federated finetuning of language models","volume":"37","author":"Panchal","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref49","article-title":"DAGER: Exact gradient inversion for large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Petrov","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.303"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0461"},{"key":"ref52","article-title":"Federated full-parameter tuning of billion-sized language models with communication cost under 18 kilobytes","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Qin","year":"2024"},{"key":"ref53","article-title":"Adaptive federated optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Reddi","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0805-8_12"},{"key":"ref55","article-title":"Position: Will we run out of data? Limits of LLM scaling based on human-generated data","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Villalobos","year":"2024"}],"container-title":["IEEE Transactions on Computational Social Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570650\/11272985\/11073569.pdf?arnumber=11073569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T08:02:30Z","timestamp":1764748950000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11073569\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":55,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcss.2025.3575623","relation":{},"ISSN":["2329-924X","2373-7476"],"issn-type":[{"value":"2329-924X","type":"electronic"},{"value":"2373-7476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}