Fed-HeLLo: Efficient Federated Foundation Model Fine-Tuning with Heterogeneous LoRA Allocation

• URL: http://arxiv.org/abs/2506.12213v1
• Date: Fri, 13 Jun 2025 20:31:17 GMT
• Title: Fed-HeLLo: Efficient Federated Foundation Model Fine-Tuning with Heterogeneous LoRA Allocation
• Authors: Zikai Zhang, Ping Liu, Jiahao Xu, Rui Hu,
• Abstract summary: Federated Learning has recently been utilized to collaboratively fine-tune foundation models across multiple clients.<n>Most existing methods do not account for the heterogeneous resources of clients or lack an effective local training strategy.<n>We propose Fed-HeLLo, a novel federated LoRA-based fine-tuning framework that enables clients to collaboratively fine-tune an FM with different local trainable LoRA layers.
• Score: 11.10244162253018
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated Learning has recently been utilized to collaboratively fine-tune foundation models across multiple clients. Notably, federated low-rank adaptation LoRA-based fine-tuning methods have recently gained attention, which allows clients to fine-tune FMs with a small portion of trainable parameters locally. However, most existing methods do not account for the heterogeneous resources of clients or lack an effective local training strategy to maximize global fine-tuning performance under limited resources. In this work, we propose Fed-HeLLo, a novel federated LoRA-based fine-tuning framework that enables clients to collaboratively fine-tune an FM with different local trainable LoRA layers. To ensure its effectiveness, we develop several heterogeneous LoRA allocation (HLA) strategies that adaptively allocate local trainable LoRA layers based on clients' resource capabilities and the layer importance. Specifically, based on the dynamic layer importance, we design a Fisher Information Matrix score-based HLA that leverages dynamic gradient norm information. To better stabilize the training process, we consider the intrinsic importance of LoRA layers and design a Geometrically-Defined HLA strategy. It shapes the collective distribution of trainable LoRA layers into specific geometric patterns, such as Triangle, Inverted Triangle, Bottleneck, and Uniform. Moreover, we extend GD-HLA into a randomized version, named Randomized Geometrically-Defined HLA, for enhanced model accuracy with randomness. By co-designing the proposed HLA strategies, we incorporate both the dynamic and intrinsic layer importance into the design of our HLA strategy. We evaluate our approach on five datasets under diverse federated LoRA fine-tuning settings, covering three levels of data distribution from IID to extreme Non-IID. Results show that Fed-HeLLo with HLA strategies is both effective and efficient.

Related papers

• HiLoRA: Hierarchical Low-Rank Adaptation for Personalized Federated Learning [11.466314810697169]
  Low-Rank Adaptation (LoRA) provides efficient and communication-friendly way to adapt Vision Transformers (ViTs)<n>We propose HiLoRA, a hierarchical LoRA framework that places adapters at three levels: root, cluster, and leaf.<n>We develop a LoRA-Subspace Adaptive Clustering mechanism that infers latent client groups via subspace similarity analysis.
  arXiv  Detail & Related papers  (2026-03-03T09:25:16Z)
• Unleashing MLLMs on the Edge: A Unified Framework for Cross-Modal ReID via Adaptive SVD Distillation [48.88299242238335]
  Cross-Modal Re-identification (CM-ReID) faces challenges due to maintaining a fragmented ecosystem of specialized cloud models.<n>We propose MLLMEmbed-ReID, a unified framework based on a powerful cloud-edge architecture.
  arXiv  Detail & Related papers  (2026-02-13T13:48:08Z)
• Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning [48.66442009036754]
  Low-Rank Adaptation (LoRA) is the prevailing approach for efficient large language model fine-tuning.<n>In this work, we re-evaluate four representative LoRA variants alongside vanilla LoRA.<n>We find that different LoRA methods favor distinct learning rate ranges.
  arXiv  Detail & Related papers  (2026-02-04T19:36:20Z)
• FediLoRA: Heterogeneous LoRA for Federated Multimodal Fine-tuning under Missing Modalities [9.507134068207597]
  FediLoRA is a framework for federated multimodal fine-tuning under heterogeneous LoRA ranks and missing modalities.<n>It achieves superior performance over competitive baselines in both global and personalized settings.
  arXiv  Detail & Related papers  (2025-09-01T10:40:13Z)
• PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning [54.99373314906667]
  Self-supervised representation learning for point cloud has demonstrated effectiveness in improving pre-trained model performance across diverse tasks.<n>As pre-trained models grow in complexity, fully fine-tuning them for downstream applications demands substantial computational and storage resources.<n>We propose PointLoRA, a simple yet effective method that combines low-rank adaptation (LoRA) with multi-scale token selection to efficiently fine-tune point cloud models.
  arXiv  Detail & Related papers  (2025-04-22T16:41:21Z)
• Collab: Controlled Decoding using Mixture of Agents for LLM Alignment [90.6117569025754]
  Reinforcement learning from human feedback has emerged as an effective technique to align Large Language models.<n>Controlled Decoding provides a mechanism for aligning a model at inference time without retraining.<n>We propose a mixture of agent-based decoding strategies leveraging the existing off-the-shelf aligned LLM policies.
  arXiv  Detail & Related papers  (2025-03-27T17:34:25Z)
• FedALT: Federated Fine-Tuning through Adaptive Local Training with Rest-of-World LoRA [5.162783756846019]
  Fine-tuning large language models (LLMs) in federated settings enables privacy-preserving adaptation but suffers from cross-client interference due to model aggregation.<n>We propose textbfFedALT, a novel personalized federated LoRA fine-tuning algorithm.<n>We demonstrate that FedALT significantly outperforms state-of-the-art personalized federated LoRA fine-tuning methods.
  arXiv  Detail & Related papers  (2025-03-14T21:07:46Z)
• BeamLoRA: Beam-Constraint Low-Rank Adaptation [51.52097743781401]
  Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tuning methods.<n>We propose BeamLoRA, which conceptualizes each LoRA module as a beam where each rank naturally corresponds to a potential sub-solution.
  arXiv  Detail & Related papers  (2025-02-19T10:33:22Z)
• Exploring Gradient Subspaces: Addressing and Overcoming LoRA's Limitations in Federated Fine-Tuning of Large Language Models [19.533062623518674]
  This paper critically analyzes the convergence and performance guarantees of popular FL frameworks utilizing Low-Rank Adaptation (LoRA)<n>We demonstrate that direct weight averaging outperforms LoRA-based strategies, leading to superior performance for fine-tuned models.<n>Our findings show that GaLore along with direct-weight aggregation is a more effective approach, outperforming federated LoRA methods like FlexLoRA and FFA-LoRA across both text and image modalities.
  arXiv  Detail & Related papers  (2024-10-30T15:23:44Z)
• Fed-piLot: Optimizing LoRA Assignment for Efficient Federated Foundation Model Fine-Tuning [11.10244162253018]
  We introduce Fed-piLot, an efficient FedFM fine-tuning framework with optimized local LoRA assignments for heterogeneous clients. We design a Local-Global Information Gain Score (IG-Score) based value function to optimize LoRA assignment under clients' memory constraints. Experimental results on three datasets under both IID and non-IID conditions demonstrate the effectiveness and efficiency of Fed-piLot.
  arXiv  Detail & Related papers  (2024-10-14T06:36:41Z)
• Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation [58.288682735160585]
  Low-Rank Adaptation (LoRA) is a popular technique for finetuning models. LoRA often under performs when compared to full- parameter fine-tuning. We present a framework that rigorously analyzes the adaptation rates of LoRA methods.
  arXiv  Detail & Related papers  (2024-10-10T18:51:53Z)
• Enhancing Spectrum Efficiency in 6G Satellite Networks: A GAIL-Powered Policy Learning via Asynchronous Federated Inverse Reinforcement Learning [67.95280175998792]
  A novel adversarial imitation learning (GAIL)-powered policy learning approach is proposed for optimizing beamforming, spectrum allocation, and remote user equipment (RUE) association ins. We employ inverse RL (IRL) to automatically learn reward functions without manual tuning. We show that the proposed MA-AL method outperforms traditional RL approaches, achieving a $14.6%$ improvement in convergence and reward value.
  arXiv  Detail & Related papers  (2024-09-27T13:05:02Z)
• FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations [39.88985198467528]
  We introduce a new approach called FLORA that enables federated fine-tuning on heterogeneous LoRA adapters. Our approach is noise-free and seamlessly supports heterogeneous LoRA adapters.
  arXiv  Detail & Related papers  (2024-09-09T18:21:23Z)
• Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendation [50.837277466987345]
  We focus on the field of large language models (LLMs) for recommendation. We propose RecLoRA, which incorporates a Personalized LoRA module that maintains independent LoRAs for different users. We also design a Few2Many Learning Strategy, using a conventional recommendation model as a lens to magnify small training spaces to full spaces.
  arXiv  Detail & Related papers  (2024-08-07T04:20:28Z)
• Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources [31.041608465716575]
  Federated Learning (FL) has recently been applied to the parameter-efficient fine-tuning of Large Language Models (LLMs) This study introduces FlexLoRA, a simple yet effective aggregation scheme for LLM fine-tuning.
  arXiv  Detail & Related papers  (2024-02-18T08:32:59Z)
• FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients [50.13097183691517]
  In real-world federated scenarios, there often exist a multitude of heterogeneous clients with varying computation and communication resources. We propose a novel federated tuning algorithm, FedRA. In each communication round, FedRA randomly generates an allocation matrix. It reorganizes a small number of layers from the original model based on the allocation matrix and fine-tunes using adapters.
  arXiv  Detail & Related papers  (2023-11-19T04:43:16Z)
• pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning [35.59830784463706]
  Federated learning (FL) is an emerging machine learning paradigm in which a central server coordinates multiple participants (clients) collaboratively to train on decentralized data. We propose a novel and efficient model-heterogeneous personalized Federated learning framework based on LoRA tuning (pFedLoRA) Experiments on two benchmark datasets demonstrate that pFedLoRA outperforms six state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-10-20T05:24:28Z)

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.