Pith. sign in

REVIEW 18 cited by

Improving LoRA in Privacy-preserving Federated Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.12313 v1 pith:EE56KQGK submitted 2024-03-18 cs.LG cs.CRcs.DC

Improving LoRA in Privacy-preserving Federated Learning

classification cs.LG cs.CRcs.DC
keywords lorafederatedffa-loramatricesperformancecomputationalefficiencyfine-tuning
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Low-rank adaptation (LoRA) is one of the most popular task-specific parameter-efficient fine-tuning (PEFT) methods on pre-trained language models for its good performance and computational efficiency. LoRA injects a product of two trainable rank decomposition matrices over the top of each frozen pre-trained model module. However, when applied in the setting of privacy-preserving federated learning (FL), LoRA may become unstable due to the following facts: 1) the effects of data heterogeneity and multi-step local updates are non-negligible, 2) additive noise enforced on updating gradients to guarantee differential privacy (DP) can be amplified and 3) the final performance is susceptible to hyper-parameters. A key factor leading to these phenomena is the discordance between jointly optimizing the two low-rank matrices by local clients and separately aggregating them by the central server. Thus, this paper proposes an efficient and effective version of LoRA, Federated Freeze A LoRA (FFA-LoRA), to alleviate these challenges and further halve the communication cost of federated fine-tuning LLMs. The core idea of FFA-LoRA is to fix the randomly initialized non-zero matrices and only fine-tune the zero-initialized matrices. Compared to LoRA, FFA-LoRA is motivated by practical and theoretical benefits in privacy-preserved FL. Our experiments demonstrate that FFA-LoRA provides more consistent performance with better computational efficiency over vanilla LoRA in various FL tasks.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 18 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Probing Memorization of Tabular In-Context Learning

    cs.LG 2026-06 unverdicted novelty 7.0

    A new probing framework detects moderate parametric memorization signals in tabular in-context learning models under single-task fine-tuning, strongest on low-cardinality tasks, but signals largely disappear under rea...

  2. Adaptive Selection of LoRA Components in Privacy-Preserving Federated Learning

    cs.LG 2026-05 unverdicted novelty 7.0

    AS-LoRA adaptively chooses which LoRA factor to update per layer and round using a curvature-aware second-order score, eliminating reconstruction error floors and improving performance in DP federated learning.

  3. Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges

    cs.IR 2026-05 unverdicted novelty 6.0

    A systematic review of over 200 studies concludes that LLMs in recommender systems act as a double-edged sword, creating both opportunities and new risks for trustworthiness.

  4. FedSmoothLoRA: Toward Smoother and Faster Convergence in Federated Low-Rank Adaptation

    cs.CV 2026-05 unverdicted novelty 6.0

    FedSmoothLoRA improves federated LoRA fine-tuning by constructing local initializations from a round-matching matrix for cross-round continuity and a gradient-aligned matrix for client-specific guidance, yielding fast...

  5. Task-Centric Personalized Federated Fine-Tuning of Language Models

    cs.LG 2026-03 unverdicted novelty 6.0

    FedRouter clusters adapters locally per task samples and globally across clients to create task-centric personalized models, improving generalization and reducing task interference in federated fine-tuning.

  6. FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning

    cs.LG 2026-02 conditional novelty 6.0

    A federated LoRA fine-tuning method that builds a client-similarity tree and adapts aggregation depth layer-by-layer outperforms flat or global aggregation baselines on NLU and NLG tasks.

  7. Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation

    cs.LG 2025-09 conditional novelty 6.0

    PrunedLoRA tunes large-rank LoRA adapters and progressively structurally prunes A and B to a target low rank, empirically closing much of the LoRA-to-full-fine-tuning gap.

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

    cs.LG 2025-05 unverdicted novelty 6.0

    Fed-TaLoRA uses task-agnostic low-rank residual adaptation with post-aggregation calibration to enable efficient federated continual fine-tuning across sequential tasks under non-IID conditions.

  9. Dysco: Dynamic Subspace Boosting to Mitigate LoRA Interference in Federated Learning

    cs.LG 2026-07 conditional novelty 5.0

    Dysco reduces cross-client interference in federated LoRA fine-tuning by fixing each client's update subspace to directions insensitive to other clients' activations, yielding tighter bounds and better benchmark accuracy.

  10. Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models

    cs.CR 2026-07 conditional novelty 5.0

    An edge-cloud LLM serving scheme splits the final projection along the hidden dimension, keeps cache control and LoRA modules on-device, and reports 29-46% lower per-token latency and 56-67% lower downlink payloads th...

  11. LAARA: Layer-Aware Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning

    cs.LG 2026-07 conditional novelty 5.0

    LAARA allocates LoRA ranks per layer from diagonal Fisher (gradient-based) estimates, reporting improved accuracy with fewer trainable parameters on GLUE and MathInstruct.

  12. AlignFed: Alignment-Aware Asynchronous Federated Fine-Tuning for Large Language Models in Heterogeneous Edge Environments

    cs.CL 2026-06 unverdicted novelty 5.0

    AlignFed introduces a multi-stage semantic alignment mechanism for asynchronous federated fine-tuning of LLMs to mitigate model drift, client drift, and aggregation unfairness in heterogeneous edge environments.

  13. Amortizing Federated Adaptation: Hypernetwork Driven LoRA for Personalized Foundation Models

    cs.AI 2026-06 unverdicted novelty 5.0

    HyperLoRA amortizes federated LoRA adaptation via hypernetwork-generated initializations and product-space aggregation to fix structural bias and initialization lag.

  14. FedDetox: Robust Federated SLM Alignment via On-Device Data Sanitization

    cs.CR 2026-04 unverdicted novelty 5.0

    FedDetox uses on-device knowledge-distilled classifiers to sanitize toxic data in federated SLM training, preserving safety alignment comparable to centralized baselines.

  15. A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search

    cs.CL 2026-01 conditional novelty 5.0

    LLM embeddings plus Bayesian optimization find better LoRA hyperparameters in ~30 proxy trials than standard published settings.

  16. ParaBlock: Communication-Computation Parallel Block Coordinate Federated Learning for Large Language Models

    cs.LG 2025-11 conditional novelty 5.0

    ParaBlock hides communication latency in federated block-coordinate LLM fine-tuning by running last round's upload/download in parallel with current computation, preserving the O(1/√T) convergence rate.

  17. FediLoRA: Practical Federated Fine-Tuning of Foundation Models Under Missing-Modality Constraints

    cs.LG 2025-09 unverdicted novelty 4.0

    FediLoRA is a lightweight federated LoRA aggregation method that jointly mitigates missing modalities and heterogeneous ranks in collaborative fine-tuning of foundation models.

  18. Low-Rank Adaptation Redux for Large Models

    cs.LG 2026-04 unverdicted novelty 3.0

    An overview revisits LoRA variants by categorizing advances in architectural design, efficient optimization, and applications while linking them to classical signal processing tools for principled fine-tuning.