arXiv cs.AI· Victor H. Chen, Hairui Yu, Stella K. Chung, Hong Yan·· 10 小时前AI 评分12
CIDERS：通过加速个性化双层优化实现云边 LLM 协同学习
CIDERS: Cloud-Edge LLM Collaborative Learning via Accelerating Personalized Bilevel Optimization
AI 导读
论文提出 CIDERS，一种将云边 LLM 协同建模为个性化双层优化框架的高效求解器，把模型分解为可学习骨干与 messenger，通过共识变量校正将全局轨迹嵌入本地个性化步骤。实验显示其在压缩边缘路径上数学推理和代码生成分别取得 3.1x 和 1.7x 提升，指令指标相对提升 10%。该论文因实验存在关键问题已被作者撤回。
正文 · 原文
This paper has been withdrawn by Yi Yuan Dr
No PDF available, click to view other formats
Abstract:Amid the rapid advancement of physical-world intelligence, cloud-edge collaborative large language models (LLMs) have emerged as a promising roadmap for practical LLM deployment. However, existing cloud-edge paradigms struggle to balance global consensus with local personalization, which fails to satisfy the need for a unified knowledge foundation on the cloud and domain-specific adaptation at the edge. To address this, we introduce, for the first time, a personalized bilevel optimization framework that formalizes cloud-edge LLM collaboration as a dual structure: the upper level optimizes edge-side personalization, while the lower level governs cloud-side knowledge transfer, reaching cloud-edge evolving in coordination. We then propose CIDERS, an efficient solver that decomposes the model into a learnable backbone and a messenger. While the cloud performs knowledge transfer to the learnable backbone, the key lies in embedding global trajectories into each local personalization step via consensus-variate correction to reconcile personalization with consensus. We provide a comprehensive theoretical analysis, including a geometric characterization of the local trajectory and a full convergence guarantee, revealing an explicit trade-off structure between personalization and global convergence. Extensive experiments demonstrate that CIDERS consistently outperforms competitive baselines on the compressed edge path, with 3.1x and 1.7x gains on mathematical reasoning and code generation, respectively, and a 10\% relative gain on instruction metrics. Mechanism experiments attribute these gains to early consensus-corrected coordination and task-aware distillation. Overall, CIDERS offers a viable path toward consensus-guided continuous personalization in cloud-edge LLM systems.
| Comments: | There are several key inssues in our experiment that we must withdraw as soon as possible to avoid any misleading |
| Subjects: | Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.15664 [cs.DC] |
| (or arXiv:2609.15664v3 [cs.DC] for this version) | |
| https://doi.org/10.48550/arXiv.2609.15664 arXiv-issued DOI via DataCite |
Submission history
From: Yi Yuan Dr [view email]
[v1]
Mon, 14 Sep 2026 14:45:24 UTC (1,468 KB)
[v2]
Sun, 8 Nov 2026 02:15:28 UTC (1 KB) (withdrawn)
[v3]
Tue, 10 Nov 2026 07:53:02 UTC (1 KB) (withdrawn)
来源：arXiv cs.AI · arxiv.org