FedSpaLLM: Federated Pruning of Large Language Models

• URL: http://arxiv.org/abs/2410.14852v1
• Date: Fri, 18 Oct 2024 20:33:12 GMT
• Title: FedSpaLLM: Federated Pruning of Large Language Models
• Authors: Guangji Bai, Yijiang Li, Zilinghan Li, Liang Zhao, Kibaek Kim,
• Abstract summary: Large Language Models (LLMs) achieve state-of-the-art performance but are challenging to deploy due to their high computational and storage demands. We propose FedSpaLLM, the first federated learning framework designed specifically for pruning LLMs.
• Score: 8.45879077052023
• License:
• Abstract: Large Language Models (LLMs) achieve state-of-the-art performance but are challenging to deploy due to their high computational and storage demands. Pruning can reduce model size, yet existing methods assume public access to calibration data, which is impractical for privacy-sensitive applications. To address the challenge of pruning LLMs in privacy-preserving settings, we propose FedSpaLLM, the first federated learning framework designed specifically for pruning LLMs. FedSpaLLM enables clients to prune their models locally based on private data while accounting for system heterogeneity and maintaining communication efficiency. Our framework introduces several key innovations: (1) a novel $\ell_0$-norm aggregation function that ensures only non-zero weights are averaged across clients, preserving important model parameters; (2) an adaptive mask expansion technique that meets global sparsity targets while accommodating client-specific pruning decisions; and (3) a layer sampling strategy that reduces communication overhead and personalizes the pruning process based on client resources. Extensive experiments show that FedSpaLLM improves pruning performance in diverse federated settings. The source code will be released upon publication.

Related papers

• Client-Centric Federated Adaptive Optimization [78.30827455292827]
  Federated Learning (FL) is a distributed learning paradigm where clients collaboratively train a model while keeping their own data private. We propose Federated-Centric Adaptive Optimization, which is a class of novel federated optimization approaches.
  arXiv  Detail & Related papers  (2025-01-17T04:00:50Z)
• Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions [59.5243730853157]
  Federated learning (FL) provides a privacy-preserving solution for fine-tuning pre-trained large language models (LLMs) using distributed private datasets. This article conducts a comparative analysis of three advanced federated LLM (FedLLM) frameworks that integrate knowledge distillation (KD) and split learning (SL) to mitigate these issues.
  arXiv  Detail & Related papers  (2025-01-08T11:37:06Z)
• Robust Federated Learning in the Face of Covariate Shift: A Magnitude Pruning with Hybrid Regularization Framework for Enhanced Model Aggregation [1.519321208145928]
  Federated Learning (FL) offers a promising framework for individuals aiming to collaboratively develop a shared model. variations in data distribution among clients can profoundly affect FL methodologies, primarily due to instabilities in the aggregation process. We propose a novel FL framework, combining individual parameter pruning and regularization techniques to improve the robustness of individual clients' models to aggregate.
  arXiv  Detail & Related papers  (2024-12-19T16:22:37Z)
• FedDTPT: Federated Discrete and Transferable Prompt Tuning for Black-Box Large Language Models [14.719919025265224]
  Fine-tuning large language models (LLMs) with data from specific scenarios poses privacy leakage risks. We propose for the first time a federated discrete and transferable prompt tuning, namely FedDTPT, for black-box large language models. Our approach achieves higher accuracy, reduced communication overhead, and robustness to non-iid data in a black-box setting.
  arXiv  Detail & Related papers  (2024-11-01T19:19:23Z)
• FedMoE: Personalized Federated Learning via Heterogeneous Mixture of Experts [4.412721048192925]
  We present FedMoE, the efficient personalized Federated Learning framework to address data heterogeneity. FedMoE is composed of two fine-tuning stages. In the first stage, FedMoE simplifies the problem by conducting a search based on observed activation patterns. In the second stage, these submodels are distributed to clients for further training and returned for server aggregating.
  arXiv  Detail & Related papers  (2024-08-21T03:16:12Z)
• Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes [53.4856038354195]
  Pre-trained large language models (LLMs) need fine-tuning to improve their responsiveness to natural language instructions. FedKSeed employs zeroth-order optimization with a finite set of random seeds. It significantly reduces transmission requirements between the server and clients to just a few random seeds.
  arXiv  Detail & Related papers  (2023-12-11T13:03:21Z)
• Efficient Federated Prompt Tuning for Black-box Large Pre-trained Models [62.838689691468666]
  We propose Federated Black-Box Prompt Tuning (Fed-BBPT) to optimally harness each local dataset. Fed-BBPT capitalizes on a central server that aids local users in collaboratively training a prompt generator through regular aggregation. Relative to extensive fine-tuning, Fed-BBPT proficiently sidesteps memory challenges tied to PTM storage and fine-tuning on local machines.
  arXiv  Detail & Related papers  (2023-10-04T19:30:49Z)
• FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models [22.29061931122386]
  Pre-trained language models (PLM) have revolutionized the NLP landscape, achieving stellar performances across diverse tasks. This paper introduces Federated Black-box Prompt Tuning (FedBPT), a framework designed to address these challenges.
  arXiv  Detail & Related papers  (2023-10-02T16:43:14Z)
• Towards Instance-adaptive Inference for Federated Learning [80.38701896056828]
  Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. In this paper, we present a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework. Our experiments show that our FedIns outperforms state-of-the-art FL algorithms, e.g., a 6.64% improvement against the top-performing method with less than 15% communication cost on Tiny-ImageNet.
  arXiv  Detail & Related papers  (2023-08-11T09:58:47Z)
• Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
  We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
  arXiv  Detail & Related papers  (2023-05-01T20:04:46Z)
• User-Centric Federated Learning: Trading off Wireless Resources for Personalization [18.38078866145659]
  In Federated Learning (FL) systems, Statistical Heterogeneousness increases the algorithm convergence time and reduces the generalization performance. To tackle the above problems without violating the privacy constraints that FL imposes, personalized FL methods have to couple statistically similar clients without directly accessing their data. In this work, we design user-centric aggregation rules that are based on readily available gradient information and are capable of producing personalized models for each FL client. Our algorithm outperforms popular personalized FL baselines in terms of average accuracy, worst node performance, and training communication overhead.
  arXiv  Detail & Related papers  (2023-04-25T15:45:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.