{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:12:08Z","timestamp":1788844328391,"version":"build-2803163510"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62273089,62406079"],"award-info":[{"award-number":["62273089,62406079"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/icws72778.2026.00116","type":"proceedings-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:19:45Z","timestamp":1788808785000},"page":"967-977","source":"Crossref","is-referenced-by-count":0,"title":["FedAlloy: Dual-Channel Federated Learning Across Quantized and Heterogeneous Language Models"],"prefix":"10.1109","author":[{"given":"Jianfeng","family":"Ling","sequence":"first","affiliation":[{"name":"Guangdong University of Technology","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feilong","family":"Feng","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinquan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihong","family":"Wan","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"McMahan","year":"2017"},{"key":"ref2","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proceedings of Machine learning and systems","volume":"2","author":"Li","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671582"},{"key":"ref4","article-title":"FATE-LLM: A industrial grade federated learning framework for large language models","author":"Fan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hu","year":"2022"},{"key":"ref6","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","volume-title":"International Conference on Learning Representations (ICLR)","author":"Frantar","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.67"},{"key":"ref9","article-title":"HAFLQ: Heterogeneous adaptive federated lora fine-tuned llm with quantization","volume-title":"2025 IEEE International Conference on Communications (ICC)","author":"Su","year":"2025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref11","article-title":"TinyLlama: An open-source small language model","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"FedMD: Heterogeneous federated learning via model distillation","volume-title":"NeurIPS 2019 Workshop on Federated Learning for Data Privacy and Confidentiality","author":"Li","year":"2019"},{"key":"ref14","first-page":"243","article-title":"FedMKT: Federated mutual knowledge transfer for large and small language models","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics","author":"Fan","year":"2025"},{"key":"ref15","article-title":"Think locally, act globally: Federated learning with local and global representations","volume-title":"NeurIPS 2019 Workshop on Federated Learning for Data Privacy and Confidentiality","author":"Liang","year":"2019"},{"key":"ref16","article-title":"QA-LoRA: Quantization-aware low-rank adaptation of large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Xu","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.632"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/085713-4009"},{"key":"ref19","article-title":"Fed-SB: A silver bullet for extreme communication efficiency and performance in (private) federated LoRA fine-tuning","author":"Singhal","year":"2025","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Federated large language models: Current progress and future directions","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/BigData62323.2024.10825769"},{"key":"ref22","first-page":"2351","article-title":"Ensemble distillation for robust model fusion in federated learning","volume":"33","author":"Lin","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/085713-2753"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS67624.2025.00046"},{"key":"ref25","first-page":"87","article-title":"AWQ: Activation-aware weight quantization for on-device LLM compression and acceleration","volume-title":"Proceedings of machine learning and systems","volume":"6","author":"Lin","year":"2024"},{"key":"ref26","first-page":"196","article-title":"Atom: Low-bit quantization for efficient and accurate LLM serving","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Zhao","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS62655.2024.00099"},{"key":"ref29","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1300"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1128"},{"key":"ref32","article-title":"Think you have solved question answering? try ARC, the AI2 reasoning challenge","author":"Clark","year":"2018","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.449"},{"key":"ref34","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref35","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"BLOOM: A 176b-parameter open-access multilingual language model","volume-title":"arXiv preprint","author":"Workshop","year":"2022"},{"key":"ref37","article-title":"Qwen2.5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","year":"2019"}],"event":{"name":"2026 IEEE International Conference on Web Services (ICWS)","location":"Sydney, Australia","start":{"date-parts":[[2026,7,13]]},"end":{"date-parts":[[2026,7,18]]}},"container-title":["2026 IEEE International Conference on Web Services (ICWS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11670018\/11670022\/11670171.pdf?arnumber=11670171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T04:53:37Z","timestamp":1788843217000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11670171\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icws72778.2026.00116","relation":{},"subject":[],"published":{"date-parts":[[2026,7]]}}}