Metraipolis › archive › dc_11ec262a7e75
CARE-FL: Federated Fine-Tuning of Multimodal LLMs in Resource-Constrained Edge Networks — arXiv:2611.06169
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06169
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:19:20.708Z
- SHA-256 of the archived text
6adf7c7ffcc69e8108a3d2276d63aafbf958d238564b1ce61d00bcf676ae10cc- Stable URL of this page
https://metraipolis.com/documento/dc_11ec262a7e75
How to cite
CARE-FL: Federated Fine-Tuning of Multimodal LLMs in Resource-Constrained Edge Networks — arXiv:2611.06169 — arXiv (en), https://arxiv.org/abs/2611.06169 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_11ec262a7e75 (Metraipolis archive dc_11ec262a7e75, sha256 6adf7c7ffcc69e8108a3d2276d63aafbf958d238564b1ce61d00bcf676ae10cc)
BibTeX
@misc{dc11ec262a7e75,
title = {CARE-FL: Federated Fine-Tuning of Multimodal LLMs in Resource-Constrained Edge Networks — arXiv:2611.06169},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06169},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_11ec262a7e75; sha256 6adf7c7ffcc69e8108a3d2276d63aafbf958d238564b1ce61d00bcf676ae10cc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06169. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Domain-specific adaptation of Multimodal Large Language Models (MLLMs) in privacy-sensitive edge environments requires federated fine-tuning, yet client selection remains challenging due to heterogeneous multimodal data and modality availability, dynamic system conditions, and evolving client utility during training. We propose Constraint-Aware Reinforcement Learning for Efficient Federated Fine-Tuning (CARE-FL), a constrained online client-selection framework for federated MLLM Low-Rank Adaptation (LoRA) fine-tuning. CARE-FL formulates client participation as a sequential decision process and employs Q-value decomposition to address the large combinatorial joint action space through scalable client-level long-term utility estimation. These utilities are learned online using a modified Double Deep Q-Learning (DDQL) scheme, while constraint-aware $\epsilon$-greedy execution selects feasible client subsets under per-round latency and bandwidth constraints. Complementing client selection, an adaptive aggregation mechanism further controls potentially unstable global updates and places greater weight on the previous model when needed. Experiments on the CrisisMMD disaster-response task in emulated heterogeneous wireless edge environments show that CARE-FL achieves higher and more stable test accuracy than the compared client-selection baselines across different system settings, while satisfying the imposed latency and bandwidth constraints. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2611.06169 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-05T18:13:18.987Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).