Skip to content

CIDERS: Cloud-Edge LLM Collaborative Learning via Accelerating Personalized Bilevel Optimization

Sep 2026 · arXiv.org · Vol abs/2609.15664 · 0 citations · 60 references
Computer Science

TL;DR

This work introduces, 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.

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.

View source

Similar papers

#artificial intelligence Preprint Oct 2026

DySCo: Dynamic Sharding for Collaborative Edge-Cloud LLM Inference with Depth-Synchronized Batching

Pervasive intelligent applications are increasingly deployed on mobile and Internet of Things (IoT) edge devices. Consequently, Large Language Models (LLMs) are increasingly used to support these applications. Yet, due to their high resource demands, LLMs are mostly deployed in the cloud. Layer-wise edge-cloud inferenc...

Jing-Po Xu, Paul Joe Maliakel, Ivona Brandić et al. · 0 citations
Preprint Oct 2026

DS-Net: A Dynamic Split Network for Edge-Cloud Collaborative Inference

Collaborative inference serves as a critical methodology in edge intelligence. Existing collaborative inference methods operate by splitting the deep neural network (DNN) model between edge devices and cloud servers. However, these methods need to load different models for multiple split points when the communication o...

Xin-Yun Zhang, Li Wang, Lei Jin et al. · 0 citations
#federated learning Book Open access Nov 2026

FedCSOT: Model-Heterogeneous Personalized Federated Learning via Channel Semantic Optimal Transport

Federated Learning (FL) provides a privacy-preserving paradigm for collaborative learning across distributed clients. In practical FL systems, clients often exhibit non-IID data distributions and deploy diverse model architectures under resource constraints. While model heterogeneity improves deployment flexibility und...

Yi-Heng Li, Huan Zhou, Xiu-Hua Li et al. · 0 citations
#federated learning Book Open access Nov 2026

FrozenSFL: Model-Frozen Split Federated Learning for Resource-Efficient LLM Fine-Tuning over Heterogeneous Edge Devices

This paper proposes FrozenSFL, a resource-efficient SFL framework for collaborative fine-tuning of LLMs across heterogeneous edge devices, and introduces a server-side feature caching mechanism that reuses invariant features, allowing subsequent training epochs to proceed offline and reducing redundant computation and...

Xiao-Pei Chen, Wen Wu, Liang Li et al. · 0 citations
Conference Open access 2026

AI-native 6G Network based on Large Language Model (LLM)

The sixth-generation (6G) mobile communication is evolving towards the AI-native paradigm of integrated communication, sensing, computing and intelligence. The stringent requirements from vertical scenarios such as the Industrial Internet and autonomous driving have increasingly exposed the inherent bottlenecks of trad...

Yu-Jie Zhai · 0 citations
Preprint Oct 2026

HintKD: Hint Knowledge Distillation for Bandwidth-Constrained Cloud-Edge Inference

Collaborative inference between the edge cloud and user equipment (UE) is a promising paradigm for deploying large deep neural networks (DNNs) in 6G networks. However, existing cloud-edge inference and distillation schemes often require the real-time transmission of high-dimensional intermediate features or soft probab...

Wan-Ling Luo, Jia-Yi Zhang, Bo-Kai Xu et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.