H2Tune: Federated Foundation Model Fine-Tuning with Hybrid Heterogeneity

• URL: http://arxiv.org/abs/2507.22633v2
• Date: Thu, 31 Jul 2025 01:43:24 GMT
• Title: H2Tune: Federated Foundation Model Fine-Tuning with Hybrid Heterogeneity
• Abstract summary: We propose H2Tune, a federated foundation model fine-tuning with hybrid heterogeneity.<n>Our framework consists of three key components: (i) sparsified triple matrix decomposition to align hidden dimensions across clients through constructing rank-consistent middle matrices, with adaptive sparsification based on client resources; (ii) relation-guided matrix layer alignment to handle heterogeneous layer structures and representation capabilities; and (iii) alternating task-knowledge disentanglement mechanism to decouple shared and specific knowledge of local model parameters through alternating optimization.
• Score: 25.639893635287187
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Different from existing federated fine-tuning (FFT) methods for foundation models, hybrid heterogeneous federated fine-tuning (HHFFT) is an under-explored scenario where clients exhibit double heterogeneity in model architectures and downstream tasks. This hybrid heterogeneity introduces two significant challenges: 1) heterogeneous matrix aggregation, where clients adopt different large-scale foundation models based on their task requirements and resource limitations, leading to dimensional mismatches during LoRA parameter aggregation; and 2) multi-task knowledge interference, where local shared parameters, trained with both task-shared and task-specific knowledge, cannot ensure only task-shared knowledge is transferred between clients. To address these challenges, we propose H2Tune, a federated foundation model fine-tuning with hybrid heterogeneity. Our framework H2Tune consists of three key components: (i) sparsified triple matrix decomposition to align hidden dimensions across clients through constructing rank-consistent middle matrices, with adaptive sparsification based on client resources; (ii) relation-guided matrix layer alignment to handle heterogeneous layer structures and representation capabilities; and (iii) alternating task-knowledge disentanglement mechanism to decouple shared and specific knowledge of local model parameters through alternating optimization. Theoretical analysis proves a convergence rate of O(1/\sqrt{T}). Extensive experiments show our method achieves up to 15.4% accuracy improvement compared to state-of-the-art baselines. Our code is available at https://anonymous.4open.science/r/H2Tune-1407.

Related papers

• UniFed-VLM: Federated Instruction Tuning for Vision-Language Models with Multiple Heterogeneity [82.84279796262818]
  We propose UniFed-VLM, a unified instruction tuning framework for Vision-Language Models (VLMs)<n>It consists of two key components: 1) Federated Compensated Subspace Aggregation (FedCSA), which performs subspace-aligned aggregation of parameter-efficient adapters.<n>We conduct experiments on multiple benchmark datasets, and the results show that UniFed-VLM achieves stronger average performance.
  arXiv  Detail & Related papers  (2026-08-16T04:01:04Z)
• Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients [22.724544289853558]
  FedSLM is a parameter-centric framework for federated fine-tuning with heterogeneous compressed clients.<n>We provide theoretical guarantees for adapter-level aggregation, subspace-alignment bounds for cross-group fusion, and a characterization of how the confidence loss mitigates weak-supervision noise.
  arXiv  Detail & Related papers  (2026-07-31T06:45:56Z)
• FedSPM: Routing-Enabled Federated Learning under Dual Heterogeneity via Semiparametric Mixture [14.751907622686423]
  We present FedSPM, a routing-enabled semiparametric mixture framework that represents each client using client-specific latent components.<n>Experiments on controlled benchmarks and real-world medical data demonstrate consistent improvements in routing and prediction under dual heterogeneity.
  arXiv  Detail & Related papers  (2026-07-05T02:31:39Z)
• From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning [23.704003173950905]
  Heterogeneous federated learning (HtFL) aims to enable collaboration among clients that differ in both data distributions and model architectures.<n>Existing prototype-based HtFL methods typically reuse the MSE-based or cosine-based alignment mechanism.<n>We propose FedSAF, which shifts the alignment objective from absolute coordinates to inter-class relational structure.
  arXiv  Detail & Related papers  (2026-05-07T10:06:26Z)
• Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models [63.70401095689976]
  Vision-Language Models (VLMs) have broad potential in privacy-sensitive domains such as healthcare and finance.<n>We propose MoR, a federated alignment framework that combines GRPO with Mixture-of-Rewards for heterogeneousVLMs.<n>MoR consistently outperforms federated alignment baselines in generalization and cross-client adaptability.
  arXiv  Detail & Related papers  (2026-05-05T07:02:50Z)
• SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated Learning [52.27042894010677]
  Spiking Federated Learning (SFL) has been widely studied with the energy efficiency of Spiking Neural Networks (SNNs)<n>We introduce SFedHIFI, a novel Spiking Federated Learning framework with Fire Rate-Based Heterogeneous Information Fusion.
  arXiv  Detail & Related papers  (2026-03-16T08:13:03Z)
• Generative Data Transformation: From Mixed to Unified Data [57.84692191369066]
  textscTaesar is a emphdata-centric framework for textbftarget-textbfal textbfregeneration.<n>It encodes cross-domain context into target sequences, enabling standard models to learn intricate dependencies without complex fusion architectures.
  arXiv  Detail & Related papers  (2026-02-26T08:30:09Z)
• Wireless Federated Multi-Task LLM Fine-Tuning via Sparse-and-Orthogonal LoRA [61.12136997430116]
  Decentralized federated learning (DFL) based on low-rank adaptation (LoRA) enables mobile devices with multi-task datasets to collaboratively fine-tune a large language model (LLM) by exchanging locally updated parameters with a subset of neighboring devices via wireless connections for knowledge integration.<n> directly aggregating parameters fine-tuned on heterogeneous datasets induces three primary issues across the DFL life-cycle: (i) catastrophic knowledge forgetting during fine-tuning process, arising from conflicting update directions caused by data heterogeneity; (ii) textitinefficient communication and convergence during model aggregation process,
  arXiv  Detail & Related papers  (2026-02-24T02:45:32Z)
• Fine-Grained Model Merging via Modular Expert Recombination [33.253051407398836]
  We propose MERGE, a method that enables component-wise model merging and input-aware, on-demand module recombination at inference.<n> MERGE formulates component-wise merging as a bi-objective optimization problem that balances cross-task performance and storage efficiency.<n>We show that MERGE consistently outperforms strong baselines and generalizes effectively.
  arXiv  Detail & Related papers  (2026-02-06T09:55:56Z)
• CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval [54.15776146365823]
  Composed Image Retrieval (CIR) enables users to search for target images using both a reference image and manipulation text.<n>We propose CSMCIR, a unified representation framework that achieves efficient query-target alignment through three synergistic components.
  arXiv  Detail & Related papers  (2026-01-07T09:21:38Z)
• scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration [53.683726781791385]
  We introduce a scalable and flexible generative framework called single-cell Multi-omics Regularized Disentangled Representations (scMRDR) for unpaired multi-omics integration.<n>Our method achieves excellent performance on benchmark datasets in terms of batch correction, modality alignment, and biological signal preservation.
  arXiv  Detail & Related papers  (2025-10-28T21:28:39Z)
• Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression [14.086434595924716]
  Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead.<n>We introduce a unified framework based on dynamic expert clustering and structured compression to address these issues cohesively.
  arXiv  Detail & Related papers  (2025-09-27T10:45:58Z)
• H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction [39.22287224290769]
  H3R is a hybrid framework that integrates latent fusion with attention-based feature aggregation.<n>By integrating both paradigms, our approach enhances generalization while converging 2$times$ faster than existing methods.<n>Our method supports variable-number and high-resolution input views while demonstrating robust cross-dataset generalization.
  arXiv  Detail & Related papers  (2025-08-05T05:56:30Z)
• Cross-architecture universal feature coding via distribution alignment [88.73189953617594]
  We introduce a new research problem: cross-architecture universal feature coding (CAUFC)<n>We propose a two-step distribution alignment method. First, we design the format alignment method that CNN and Transformer features into a consistent 2D token format. Second, we propose the feature value alignment method that harmonizes statistical distributions via truncation and normalization.<n>As a first attempt to study CAUFC, we evaluate our method on the image classification task. Experimental results demonstrate that our method achieves superior rate-accuracy trade-offs compared to the architecture-specific baseline.
  arXiv  Detail & Related papers  (2025-06-15T06:14:02Z)
• Client Selection in Federated Learning with Data Heterogeneity and Network Latencies [19.161254709653914]
  Federated learning (FL) is a distributed machine learning paradigm where multiple clients conduct local training based on their private data, then the updated models are sent to a central server for global aggregation.<n>In this paper, we propose two novel theoretically optimal client selection schemes that handle both these heterogeneities.
  arXiv  Detail & Related papers  (2025-04-02T17:31:15Z)
• A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning [0.0]
  Heterogeneity in federated learning (FL) is a critical and challenging aspect that significantly impacts model performance and convergence.<n>We propose a novel framework by formulating heterogeneous FL as a hierarchical optimization problem.<n>We implement our method on image classification tasks and compare with other methods under different heterogeneous settings.
  arXiv  Detail & Related papers  (2025-04-02T15:44:59Z)
• A Unified Solution to Diverse Heterogeneities in One-shot Federated Learning [16.120630244663452]
  One-Shot Federated Learning (OSFL) restricts communication between the server and clients to a single round.<n>FedHydra is a unified, data-free, OSFL framework designed to effectively address both model and data heterogeneity.
  arXiv  Detail & Related papers  (2024-10-28T15:20:52Z)
• Adaptive Guidance for Local Training in Heterogeneous Federated Learning [23.92461217732838]
  Model heterogeneity poses a significant challenge in Heterogeneous Federated Learning (HtFL)<n>We propose FedL2G, a method that adaptively learns to guide local training in a federated manner.<n>FedL2G significantly outperforms seven state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-09T02:31:49Z)
• Incorporating Arbitrary Matrix Group Equivariance into KANs [69.30866522377694]
  We propose Equivariant Kolmogorov-Arnold Networks (EKAN), a method for incorporating arbitrary matrix group equivariants into KANs.<n>EKAN achieves higher accuracy with smaller datasets or fewer parameters on symmetry-related tasks, such as particle scattering and the three-body problem.
  arXiv  Detail & Related papers  (2024-10-01T06:34:58Z)
• pFedAFM: Adaptive Feature Mixture for Batch-Level Personalization in Heterogeneous Federated Learning [34.01721941230425]
  We propose a model-heterogeneous personalized Federated learning approach with Adaptive Feature Mixture (pFedAFM) for supervised learning tasks. It significantly outperforms 7 state-of-the-art MHPFL methods, achieving up to 7.93% accuracy improvement.
  arXiv  Detail & Related papers  (2024-04-27T09:52:59Z)
• FLASH: Federated Learning Across Simultaneous Heterogeneities [54.80435317208111]
  FLASH(Federated Learning Across Simultaneous Heterogeneities) is a lightweight and flexible client selection algorithm. It outperforms state-of-the-art FL frameworks under extensive sources of Heterogeneities. It achieves substantial and consistent improvements over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-02-13T20:04:39Z)
• Fake It Till Make It: Federated Learning with Consensus-Oriented Generation [52.82176415223988]
  We propose federated learning with consensus-oriented generation (FedCOG) FedCOG consists of two key components at the client side: complementary data generation and knowledge-distillation-based model training. Experiments on classical and real-world FL datasets show that FedCOG consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-10T18:49:59Z)
• Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation [103.90033029330527]
  Few-Shot Instance (FSIS) requires detecting and segmenting novel classes with limited support examples. We introduce a unified framework, Reference Twice (RefT), to exploit the relationship between support and query features for FSIS.
  arXiv  Detail & Related papers  (2023-01-03T15:33:48Z)
• GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning [55.79997930181418]
  Generalized Zero-Shot Learning aims to recognize images from both the seen and unseen classes by transferring semantic knowledge from seen to unseen classes. It is a promising solution to take the advantage of generative models to hallucinate realistic unseen samples based on the knowledge learned from the seen classes. We propose a novel flow-based generative framework that consists of multiple conditional affine coupling layers for learning unseen data generation.
  arXiv  Detail & Related papers  (2022-07-05T04:04:37Z)

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.