Breaking the Structural Identity: Personalized Federated LoRA Fine-tuning under Rank Heterogeneity

• URL: http://arxiv.org/abs/2609.00632v1
• Date: Tue, 01 Sep 2026 03:09:20 GMT
• Title: Breaking the Structural Identity: Personalized Federated LoRA Fine-tuning under Rank Heterogeneity
• Abstract summary: FedRoRA is a novel framework that enables fine-grained personalization within rank-heterogeneous federations.<n>It decouples adaptation into shared global directions and personalized rank-wise magnitudes governed by learnable diagonal scales.<n>Experiments on NLU and NLG benchmarks demonstrate that FedRoRA consistently outperforms state-of-the-art methods.
• Score: 12.733972494875713
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have achieved remarkable success across diverse domains, but their adaptation to privacy-sensitive, distributed datasets remains a challenge. While Federated Learning (FL) combined with Low-Rank Adaptation (LoRA) provides a resource-efficient paradigm for collaborative fine-tuning, practical deployments are hindered by the dual challenges of resource heterogeneity and data heterogeneity. Existing rank-heterogeneous methods primarily focus on bridging dimension mismatches for aggregation but typically provide a unified global model for all clients sharing the same rank, failing to capture client-specific features in non-IID scenarios. In this paper, we propose FedRoRA (Federated Rank-wise Personalized LoRA), a novel framework that enables fine-grained personalization within rank-heterogeneous federations. FedRoRA decouples adaptation into shared global directions and personalized rank-wise magnitudes governed by learnable diagonal scales. On the server side, it extracts a global subspace via singular value decomposition (SVD) and redistributes client-specific initializations through a personalized projection and top-$k$ selection mechanism. Extensive experiments on NLU and NLG benchmarks demonstrate that FedRoRA consistently outperforms state-of-the-art methods.

Related papers

• Separate Aggregation of Split Network for Personalized Federated Learning [0.9668407688201359]
  Federated learning can degrade substantially under heterogeneous client data distributions.<n>We propose PGFedSplit, a personalized federated learning framework.<n>Experiments on Fashion MNIST, CIFAR 10, CIFAR 100, and Tiny ImageNet demonstrate consistent improvements over state of the art PFL methods.
  arXiv  Detail & Related papers  (2026-05-26T05:44:30Z)
• 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)
• FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment [55.97027207627]
  Fed PDPO (Federated Personalized Direct Preference Optimization) is a personalized framework for preference alignment of large language models (LLMs)<n>It adopts a parameter-efficient fine-tuning architecture where each client maintains a frozen pretrained LLM backbone augmented with a Low-Rank Adaptation (LoRA) adapter, enabling communication-efficient aggregation.<n>Experiments on multiple preference datasets demonstrate state-of-the-art performance, achieving up to 4.80% average accuracy improvements in federated intra-domain and cross-domain settings.
  arXiv  Detail & Related papers  (2026-03-20T08:24:49Z)
• FedPrism: Adaptive Personalized Federated Learning under Non-IID Data [1.299941371793082]
  FedPrism is a framework that builds each client's model from three parts.<n>It uses a Prism Decomposition method that builds each client's model from three parts.<n>It also uses a Dual-Stream design that runs a general model alongside a local specialist.
  arXiv  Detail & Related papers  (2026-03-09T11:23:32Z)
• FeDecider: An LLM-Based Framework for Federated Cross-Domain Recommendation [75.50721642765994]
  Large language model (LLM)-based recommendation models have demonstrated impressive performance.<n>We propose an LLM-based framework for Federated cross-domain recommendation, FeDecider.<n>Extensive experiments across diverse datasets validate the effectiveness of our proposed FeDecider.
  arXiv  Detail & Related papers  (2026-02-17T21:42:28Z)
• Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models [63.70401095689976]
  We argue that replacing parameters with preferences represents a more scalable and privacy-preserving future.<n>We propose MoR, a federated alignment framework based on GRPO with Mixture-of-Rewards for heterogeneous VLMs.<n>MoR consistently outperforms federated alignment baselines in generalization, robustness, and cross-client adaptability.
  arXiv  Detail & Related papers  (2026-01-31T03:11:51Z)
• FedUTR: Federated Recommendation with Augmented Universal Textual Representation for Sparse Interaction Scenarios [58.33672784127872]
  Federated recommendations (FRs) have emerged as an on-device privacy-preserving paradigm.<n>We propose a novel method named FedUTR, which incorporates item textual representations as a complement to interaction behaviors.<n>Our method achieves superior performance, with improvements of up to 59% across all datasets compared to the SOTA baselines.
  arXiv  Detail & Related papers  (2026-01-29T08:55:19Z)
• 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)
• Generalized and Personalized Federated Learning with Foundation Models via Orthogonal Transformations [4.008780119020479]
  Federated Learning aims to train models across decentralized clients or devices holding local data without the need for centralized data collection.<n>We introduce FedOT, a novel approach that leverages black-box foundation models.<n>FedOT mitigates gradient conflicts across diverse clients, preserves semantic integrity, and achieves robust performance even in the presence of substantial data.
  arXiv  Detail & Related papers  (2025-05-26T12:18:24Z)
• A Shared Low-Rank Adaptation Approach to Personalized RLHF [12.874322231672009]
  Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for aligning artificial intelligence systems with human values.<n>Existing RLHF frameworks often assume that human preferences are relatively homogeneous and can be captured by a single, unified reward model.<n>This paper introduces Low-Rank Adaptation (LoRA) into the personalized RLHF framework.
  arXiv  Detail & Related papers  (2025-03-24T23:01:08Z)
• Federated and Generalized Person Re-identification through Domain and Feature Hallucinating [88.77196261300699]
  We study the problem of federated domain generalization (FedDG) for person re-identification (re-ID) We propose a novel method, called "Domain and Feature Hallucinating (DFH)", to produce diverse features for learning generalized local and global models. Our method achieves the state-of-the-art performance for FedDG on four large-scale re-ID benchmarks.
  arXiv  Detail & Related papers  (2022-03-05T09:15:13Z)

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.