mlsanityData to 7 Oct 2026

CooperLLM: Cloud-Edge-End Cooperative Federated Fine-tuning for LLMs via ZOO-based Gradient Correction

arXiv 2601.12917 ↗First posted 19 Jan 2026cs.LG cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) perform well on many NLP tasks, but fine-tuning them on resource-constrained mobile devices is challenging due to high memory and computation costs, despite growing demands for privacy-preserving personalization. Federated Learning (FL) enables local-data training, yet existing methods either rely on memory-intensive backpropagation or use zeroth-order optimization (ZOO), which avoids backward passes but suffers from slow convergence and degraded accuracy. We propose CooperLLM, a cloud-assisted edge-end cooperative federated fine-tuning framework that combines ZOO on mobile devices with cloud-guided gradient rectification. Mobile clients perform lightweight ZOO updates on private data, while the cloud fine-tunes on auxiliary public data using backpropagation and injects guided perturbations to rectify local updates, improving convergence and accuracy without violating privacy. To address system bottlenecks, CooperLLM introduces pipeline scheduling and adaptive compression to overlap computation and communication and reduce memory usage. Experiments on multiple Transformer models and datasets show that CooperLLM reduces on-device memory by up to 86.4%, accelerates convergence by 8.8 ×, and improves accuracy by up to 10 percentage points over state-of-the-art ZOO-based baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 67 references that are in the map. First posted on arXiv 19 Jan 2026.

Builds on

34 of 67 references.

References · 34

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  5. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  6. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  7. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  8. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  9. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  10. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,234
  11. 2018Federated Learning with Non-IID Datacited by 1,099
  12. 2016Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Conditioncited by 526
22 more
  1. 2020AdapterHub: A Framework for Adapting Transformerscited by 441
  2. 2023Fine-Tuning Language Models with Just Forward Passescited by 337
  3. 2023Towards Building the Federated GPT: Federated Instruction Tuningcited by 184
  4. 2020A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learningcited by 160
  5. 2023FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learningcited by 146
  6. 2024Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmarkcited by 113
  7. 2018Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimizationcited by 109
  8. 2023SLoRA: Federated Parameter Efficient Fine-Tuning of Language Modelscited by 92
  9. 2020Federated Accelerated Stochastic Gradient Descentcited by 85
  10. 2021FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Taskscited by 84
  11. 2022Gradients without Backpropagationcited by 73
  12. 2024FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Modelcited by 73
  13. 2022Scaling Forward Gradient With Local Lossescited by 65
  14. 2020Robust Quantization: One Model to Rule Them Allcited by 63
  15. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  16. 2022Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learningcited by 59
  17. 2023Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytescited by 55
  18. 2024ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Cachingcited by 48
  19. 2025Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuningcited by 17
  20. 2022Federated Few-Shot Learning for Mobile NLPcited by 15
  21. 2024Thinking Forward: Memory-Efficient Federated Finetuning of Language Modelscited by 7
  22. 2025Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPUcited by 3

Built on by

Not cited yet.