English(EN) FLoKD: Adaptive Knowledge Distillation for Federated Low-Rank LLM over Wireless Networks

FLoKD框架支持通信成本降低的联邦大语言模型训练

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员开发了FLoKD，一个用于无线网络上大语言模型（LLMs）联邦学习的新框架。该方法通过传输低秩适配器（LoRA）的中间激活值而非完整参数或token级logits，利用自适应知识蒸馏，显著降低了通信开销。FLoKD通过选择性地传输信息量大的Transformer块并采用数据集选择策略来丢弃不相关样本，进一步优化了这一点。实验表明，FLoKD在通信成本降低50-65%的同时，实现了具有竞争力的准确率。 AI

影响这项研究可能能够实现通过无线网络在分布式设备上更高效、更私密的训练大语言模型。

排序理由该集群包含一篇详细介绍联邦大语言模型训练新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍联邦大语言模型训练新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Xinlu Zhang, Na Yan, Yang Su, Yansha Deng, Toktam Mahmoodi · 2026-09-15 04:00

FLoKD：无线网络上联邦低秩大语言模型的自适应知识蒸馏

arXiv:2609.13580v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong capabilities across a wide range of natural language processing tasks. However, conventional fine-tuning typically relies on centralized data collection, bringing in privacy conc…

本文如何被排名

报道来源 [1]

FLoKD：无线网络上联邦低秩大语言模型的自适应知识蒸馏

相关实体

相关话题