Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuning

• URL: http://arxiv.org/abs/2606.22878v1
• Date: Mon, 22 Jun 2026 05:43:14 GMT
• Title: Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuning
• Abstract summary: Large language models (LLMs) are increasingly deployed at the network edge to provide pervasive generative AI services.<n>We propose a priority-aware learning-unlearning correction framework that can enhance the knowledge evaluation through topology adjustment.<n> Experiments demonstrate that the proposed framework achieves robust post-event correction for both device join and leave events.
• Score: 46.1516553596062
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As large language models (LLMs) are increasingly deployed at the network edge to provide pervasive generative AI services, decentralized federated learning (DFL) provides a vital mechanism for privacy-preserving, domain-specific fine-tuning through peer-to-peer exchanges of parameter-efficient updates. However, the dynamic nature of practical decentralized edge networks, where devices may dynamically join or leave the collaborative training process, requires the system to continuously adapt to new data while selectively removing prior contributions. This correction process remains a significant bottleneck, as individual device updates become deeply entangled within the global fine-tuned parameters. To address this challenge, we propose a priority-aware learning-unlearning correction framework based on orthogonal LoRA that can enhance the knowledge evaluation through topology adjustment. Specifically, we first design an orthogonal LoRA mechanism that yields post-training contribution coordinates, enabling history-free projection addition and deletion in response to membership changes. We then analyze the correction bottleneck and develop a priority-aware policy that selects among topology refinement, local correction, proximal damping, and synchronization scheduling according to the dominant residual term. A resource allocation algorithm is further developed to allocate limited communication across layer groups, prioritizing the primary bottlenecks within per-round wireless constraints. Experiments demonstrate that the proposed framework achieves robust post-event correction for both device join and leave events and validate that different residual regimes necessitate distinct correction actions.

Related papers

• A Graph Foundation Model for Wireless Resource Allocation [37.503398874234094]
  We propose a graph foundation model for resource allocation based on a pre-training and fine-tuning paradigm to extract unified representations.<n>Specifically, we introduce an interference-aware Transformer architecture with a bias projector that injects interference topologies into global attention mechanisms.<n>Experiments demonstrate that the proposed framework achieves state-of-the-art performance and scales effectively with increased model capacity.
  arXiv  Detail & Related papers  (2026-04-08T06:07:28Z)
• 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)
• Local adapt-then-combine algorithms for distributed nonsmooth optimization: Achieving provable communication acceleration [50.67878993903822]
  We propose a communication-efficient Adapt-Then-Combine (ATC) framework, FlexATC, unifying numerous ATC-based distributed algorithms.<n>We show for the first time that local updates provably lead to communication acceleration for ATC-based distributed algorithms.
  arXiv  Detail & Related papers  (2026-02-18T02:47:05Z)
• Stabilizing Decentralized Federated Fine-Tuning via Topology-Aware Alternating LoRA [20.00589625873043]
  textttTAD-LoRA is a serverless variant of federated learning.<n>We show that textttTAD-LoRA is competitive in strongly connected topologies and delivers clear gains under moderately and weakly connected topologies.
  arXiv  Detail & Related papers  (2026-01-31T01:57:53Z)
• Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA [50.97792275353563]
  We introduce a novel framework that restructures a single Low-Rank Adaptation (LoRA) module as a decomposable Rank-1 Expert Pool.<n>Our method learns to dynamically compose a sparse, task-specific update by selecting from this expert pool, guided by the semantics of the [Guided] token.
  arXiv  Detail & Related papers  (2026-01-30T10:54:51Z)
• Dynamic Rank Reinforcement Learning for Adaptive Low-Rank Multi-Head Self Attention in Large Language Models [0.0]
  We propose Dynamic Rank Reinforcement Learning (DR-RL), a novel framework that adaptively optimize the low-rank factorization of Multi-Head Self-Attention (MHSA) in Large Language Models (LLMs)<n>DR-RL maintains downstream accuracy statistically equivalent to full-rank attention while significantly reducing Floating Point Operations (FLOPs)<n>This work bridges the gap between adaptive efficiency and theoretical rigor in MHSA, offering a principled, mathematically grounded alternative to rank reduction techniques in resource-constrained deep learning.
  arXiv  Detail & Related papers  (2025-12-17T21:09:19Z)
• Efficient Split Federated Learning for Large Language Models over Communication Networks [45.02252893286613]
  Fine-tuning pre-trained large language models (LLMs) in a distributed manner poses significant challenges on resource-constrained edge networks.<n>We propose SflLLM, a novel framework that integrates split federated learning with parameter-efficient fine-tuning techniques.<n>By leveraging model splitting and low-rank adaptation (LoRA), SflLLM reduces the computational burden on edge devices.
  arXiv  Detail & Related papers  (2025-04-20T16:16:54Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• Progressive Conservative Adaptation for Evolving Target Domains [76.9274842289221]
  Conventional domain adaptation typically transfers knowledge from a source domain to a stationary target domain. Restoring and adapting to such target data results in escalating computational and resource consumption over time. We propose a simple yet effective approach, termed progressive conservative adaptation (PCAda)
  arXiv  Detail & Related papers  (2024-02-07T04:11:25Z)
• Serverless Federated AUPRC Optimization for Multi-Party Collaborative Imbalanced Data Mining [119.89373423433804]
  Area Under Precision-Recall (AUPRC) was introduced as an effective metric. Serverless multi-party collaborative training can cut down the communications cost by avoiding the server node bottleneck. We propose a new ServerLess biAsed sTochastic gradiEnt (SLATE) algorithm to directly optimize the AUPRC.
  arXiv  Detail & Related papers  (2023-08-06T06:51:32Z)
• Decentralized Federated Reinforcement Learning for User-Centric Dynamic TFDD Control [37.54493447920386]
  We propose a learning-based dynamic time-frequency division duplexing (D-TFDD) scheme to meet asymmetric and heterogeneous traffic demands. We formulate the problem as a decentralized partially observable Markov decision process (Dec-POMDP) In order to jointly optimize the global resources in a decentralized manner, we propose a federated reinforcement learning (RL) algorithm named Wolpertinger deep deterministic policy gradient (FWDDPG) algorithm.
  arXiv  Detail & Related papers  (2022-11-04T07:39:21Z)

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.