Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning

[2505.12318] Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2505.12318 (cs) [Submitted on 18 May 2025 ( v1 ), last revised 9 Apr 2026 (this version, v2)] Title: Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning Authors: Feng Yu , Jia Hu , Geyong Min View a PDF of the paper titled Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning, by Feng Yu and 2 other authors View PDF HTML (experimental) Abstract: Federated Parameter-Efficient Fine-Tuning (Fed-PEFT) enables lightweight adaptation of large pre-trained models in federated learning settings by updating only a small subset of parameters. However, Fed-PEFT methods typically assume a fixed label space and static downstream tasks, which is restrictive in realistic application scenarios where clients continuously encounter new classes over time. This leads to an emerging problem, known as \emph{Federated Continual Fine-Tuning} (FCFT). In FCFT, clients collaboratively fine-tune a pre-trained model over a sequence of tasks, where each client observes disjoint sets of new classes over time, and task identity is unavailable at inference time. FCFT is challenging because it simultaneously suffers from severe forgetting under non-IID client data distributions, parameter growth and task-specific inference caused by task-wise modules, and aggregation inconsistency across heterogeneous clients. To address these challenges, we propose Federated Task-agnostic Low-rank Residual Adaptation (Fed-TaLoRA), a novel approach for efficient FCFT built on task-agnostic adaptation, post-aggregation model calibration, and strategic low-rank adaptation placement. Fed-TaLoRA continuously fine-tunes a single shared module across sequential tasks to avoid task-wise parameter growth, and further introduces a theoretically grounded residual weight update mechanism to calibrate the aggregated global model and improve aggregation fidelity. We provide a theoretical analysis of the convergence and aggregation behavior of Fed-TaLoRA. Extensive experiments on four benchmark datasets demonstrate that Fed-TaLoRA consistently outperforms strong baselines while reducing communication and computation costs significantly. Subjects: Machine Learning (cs.LG) Cite as: arXiv:2505.12318 [cs.LG] (or arXiv:2505.12318v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2505.12318 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Feng Yu [ view email ] [v1] Sun, 18 May 2025 09:19:13 UTC (261 KB) [v2] Thu, 9 Apr 2026 20:36:53 UTC (374 KB) Full-text links: Access Paper: View a PDF of the paper titled Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning, by Feng Yu and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2025-05 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning#173320
• When One Adapter Speaks for Many: Discovering Low-Rank Redundancy in Continual Fine-Tuning#319681
• SPACE-LoRA: Allocating Activation-Subspace Protection for Continual Learning#1128723
• Learning Locally, Revising Globally: Global Reviser for Federated Learning with Noisy Labels#189226
• Fine-Tuning Regimes Define Distinct Continual Learning Problems#126495