2026· Annual Meeting of the Association for Computational Linguistics· pp. 5749-5762· 1 citation· 34 references
Computer Science
TL;DR
iFLoRA is proposed, an improved Federated LoRA fine-tuning system for LLMs featuring pipelined error-mitigated model aggregation and adaptive matrix-wise parameter freezing and can improve time-to-target by 2.17-8.48 × than state-of-the-art methods.
Abstract
Federated low-rank adaptation (LoRA) enables multiple clients to collaboratively fine-tune large language models (LLMs) without disclosing their raw data. However, existing works often experience performance degradation due to biased model aggregation and are hindered by significant communication and computation burden, both limiting training efficiency. In this paper, we propose iFLoRA, an improved Federated LoRA fine-tuning system for LLMs featuring pipelined error-mitigated model aggregation and adaptive matrix-wise parameter freezing . Specifically, iFLoRA mitigates aggregation error by first reconstructing local update matrices from clients’ low-rank matrices. These are then aggregated into a global update, which is decomposed via singular value decomposition (SVD) to form low-rank matrices for the next round. To mitigate the overhead from SVD, iFLoRA employs a pipeline to overlap global aggregation, local computation, and communication. Additionally, iFLoRA implements an adaptive matrix-wise freezing scheme that assesses their stability and selectively freezes them for adaptively adjusted periods, alleviating client training overheads without compromising model performance. Extensive experiments on real-world datasets show that iFLoRA can improve time-to-target by 2.17-8.48 × than state-of-the-art methods. Our code is available at
Federated fine-tuning with Low-Rank Adaptation (LoRA) enables efficient collaborative adaptation of Large Language Models (LLMs) without centralizing private data. However, LoRA's two-factor parameterization creates an aggregation mismatch across clients: naively averaging the factors does not recover the average of their induced updates. This mismatch can be avoided by forming the exact aggregate in the full weight space and then recompressing it, but decomposing the resulting dense matrix is computationally expensive and memory-intensive. We propose FraQ, an efficient coordinate-space recompression method for federated LoRA. Starting from stacked factors that exactly represent the aggregate, FraQ factorizes it into an orthonormal basis and a compact coordinate matrix. It then recovers the singular spectrum from a small Gram matrix, selects the smallest rank satisfying a prescribed energy threshold, and maps the selected coordinate subspace back through the basis to construct the global adapter. Experiments on text classification and commonsense reasoning benchmarks show that FraQ achieves accuracy close to uncompressed baselines while substantially reducing downlink communication with low server-side recompression overhead.
HeteroFL-LoRA is proposed, a federated framework that enables LoRA fine-tuning across heterogeneous LFMs and introduces a Singular Matrix–Guided Subspace Projection that employs singular matrices to achieve cross-subspace mapping, enabling heterogeneous clients to aggregate their LoRA updates in a unified representation space.
Zhuojia Wu, Qi Zhang, Xuerong Zhao et al.· Proceedings of the 32nd ACM...· 0 citations
This work proposes SeFoRA, a sketch-aggregated federated LoRA algorithm in which each client transmits a linear sketch of its local updates, enabling direct aggregation at the federator, and introduces a rank-homogeneous version called SeFoRA-Ho which allows for direct adapter aggregation in this setting.
Yue Xia, Tayyebeh Jahani-Nezhad, Mayank Bakshi et al.· 1 citation
Low-Rank Adaptation (LoRA) enables communication-efficient federated fine-tuning of pretrained language models. However, integrating differential privacy (DP) into federated LoRA remains challenging: independently perturbing and aggregating its two low-rank matrices can cause aggregation mismatch and the quadratic noise term. Existing methods mitigate these issues by freezing one low-rank matrix but still rely on Euclidean aggregation, which is basis-dependent and may distort the global update. To address this limitation, we propose FedGSA, a geometry-consistent aggregation framework for differentially private federated LoRA. FedGSA represents each privatized client update as a basis-invariant subspace on the Grassmann manifold. In each communication round, clients extract low-dimensional subspaces capturing dominant update directions and encode them as projection matrices. The server aggregates these representations to estimate a geometry-consistent global update subspace and reconstructs the global LoRA factors within it, reducing distortion caused by basis misalignment, privacy noise, and heterogeneous client updates. We prove that FedGSA incurs no additional privacy loss beyond client-side DP training and establish its convergence under standard assumptions. Experiments on four GLUE tasks and a language generation benchmark demonstrate consistent improvements across privacy budgets and degrees of data heterogeneity. In particular, FedGSA improves average accuracy over the strongest baseline by 2.17% and 2.27% under $\epsilon=6$ and $\epsilon=3$, respectively.
TRISHUL is proposed, a spectral-control framework for robust federated PEFT that follows the FL no-raw-data-sharing setting but does not itself provide formal privacy guarantees, and improves convergence, stability, and final performance over federated LoRA baselines.
Federated fine-tuning is bottlenecked by communication: FedAvg and pseudo-gradient schemes transmit a payload that scales with the model, and gradient compression shrinks it by only a constant factor. We take a different lever. Mapping networks generate a network's weights from a small trainable latent through a frozen affine projection; because the map is shared and affine, averaging latents is exactly averaging the generated weights. We turn this into a practical low-bandwidth federated channel with two changes: a low-rank, seed-regenerable factorisation of the projection (cutting generator memory from ~80 GB to ~10 MB), and a delta formulation $\theta = \theta^{\mathrm{pre}} + U V^{\top} z$ that learns an additive correction around a shared centrally-pretrained base -- federated fine-tuning, which is what makes the method work at scale. A frozen orthogonal classifier head further removes the head from the payload while improving accuracy. On CIFAR-100 with ResNet-18+GroupNorm, our method (FLITE, Federated Low-rank Iterative Training Engine) communicates 1,280 floats (~5 KB) per client per round -- an 8718x reduction -- and reaches 74.67%, within ~0.5 pp of full-weight FedAvg. The averaging identity holds to floating-point precision ($6 \times 10^{-8}$); the method sits one to two orders of magnitude below PowerSGD and top-k on the bandwidth-accuracy Pareto; it matches or exceeds full-weight FedAvg under strong non-IID skew. int4 latents reach 648 bytes per round at unchanged accuracy, whereas int4 full-weight FedAvg collapses to chance.