FED-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices

• URL: http://arxiv.org/abs/2604.25421v1
• Date: Tue, 28 Apr 2026 09:29:41 GMT
• Title: FED-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices
• Abstract summary: Federated fine-tuning provides a practical route to adapt large language models (LLMs) on edge devices without centralizing private data.<n>We propose Fed-FSTQ, a Fisher-guided token quantization system primitive for communication-efficient federated LLM fine-tuning.<n>We show that Fed-FSTQ reduces cumulative uplink traffic required to reach a fixed quality threshold by 46x relative to a standard LoRA baseline, and improves end-to-end wall-clock time-to-accuracy by 52%.
• Score: 12.523170571488711
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Federated fine-tuning provides a practical route to adapt large language models (LLMs) on edge devices without centralizing private data, yet in mobile deployments the training wall-clock is often bottlenecked by straggler-limited uplink communication under heterogeneous bandwidth and intermittent participation. Although parameter-efficient fine-tuning (PEFT) reduces trainable parameters, per-round payloads remain prohibitive in non-IID regimes, where uniform compression can discard rare but task-critical signals. We propose Fed-FSTQ, a Fisher-guided token quantization system primitive for communication-efficient federated LLM fine-tuning. Fed-FSTQ employs a lightweight Fisher proxy to estimate token sensitivity, coupling importance-aware token selection with non-uniform mixed-precision quantization to allocate higher fidelity to informative evidence while suppressing redundant transmission. The method is model-agnostic, serves as a drop-in module for standard federated PEFT pipelines, e.g., LoRA, without modifying the server aggregation rule, and supports bandwidth-heterogeneous clients via compact sparse message packing. Experiments on multilingual QA and medical QA under non-IID partitions show that Fed-FSTQ reduces cumulative uplink traffic required to reach a fixed quality threshold by 46x relative to a standard LoRA baseline, and improves end-to-end wall-clock time-to-accuracy by 52%. Furthermore, enabling Fisher-guided token reduction at inference yields up to a 1.55x end-to-end speedup on NVIDIA Jetson-class edge devices, demonstrating deployability under tight resource constraints.

Related papers

• Distributed Physical Layer Authentication and Collaborative RSMA in Non-Terrestrial Networks via Graph Reinforcement Learning [2.0965265618008315]
  passive, location-aware, static eavesdroppers without access to legitimate channel state information (CSI)<n>We propose secure adaptive authentication for multi-zone systems (SAFA-MZ) that maximizes secrecy spectral efficiency (SSE)<n>Results under both colluding and non-colluding eavesdroppers show that the proposed method improves average SSE by up to 135% over single-connect transmission and 21% over the scheme without AN.
  arXiv  Detail & Related papers  (2026-09-08T21:46:12Z)
• Dynamic Entanglement-Weighted Pruning for Quantum Federated Unlearning in Supply-Chain Risk Prediction [4.205733518246009]
  Entanglement-Weighted Pruning (EWP) is an unlearning procedure for quantum federated learning.<n>We implement the full pipeline in Qiskit for a four-qubit data-re-uploading ansatz trained with FedAvg across five simulated supply-chain-risk clients.
  arXiv  Detail & Related papers  (2026-08-17T19:17:30Z)
• DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation [69.8840101036735]
  Speculative decoding accelerates Large Language Model (LLM) inference.<n>Recent parallel drafters efficiently propose long token sequences in a single forward pass, but suffer from rapid acceptance decay due to a lack of inter-token dependencies.<n>We introduce DSpark, a speculative decoding framework that unifies high- throughput parallel generation with adaptive, load-aware verification.
  arXiv  Detail & Related papers  (2026-07-06T14:28:06Z)
• WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference [56.297697169678095]
  WISV (Wireless-Informed Semantic Verification) is a novel distributed speculative decoding framework.<n>We show that WISV achieves up to a 60.8% increase in accepted length, a 37.3% reduction in interaction rounds, and a 31.4% improvement in end-to-end latency.<n>We validate WISV on a hardware testbed comprising an NVIDIA Jetson AGX Orin and an A40-equipped server.
  arXiv  Detail & Related papers  (2026-04-20T01:29:56Z)
• A Zero Added Loss Multiplexing (ZALM) Source Simulation [34.91883081037593]
  We present a modular ZALM simulator that demonstrates how design choices affect output rate and fidelity.<n>Built in NetSquid with I/R controllers, it exposes 20+ parameters, supports I/R and REALISTIC modes, and provides reusable components.<n>Using the default configuration settings, average fidelity emains constant at 0.8 but the ebit rate decreases from 0.0175 at the source to 0.0 at 50 km; narrowing the SPDC degeneracy bandwidth increases the ebit rate significantly without affecting fidelity.
  arXiv  Detail & Related papers  (2025-10-29T22:41:40Z)
• Network-Optimised Spiking Neural Network for Event-Driven Networking [2.5941336499463383]
  Spiking neural networks offer event-driven computation suited to time-critical networking tasks such as anomaly detection, local routing control, and congestion management at the edge.<n>We introduce Network-Optimised Spiking (NOS), a compact two-variable unit whose state encodes normalised queue occupancy and a recovery resource.<n>We provide guidance for data-driven initialisation, surrogate-gradient training with a homotopy on reset sharpness, and explicit stability checks with topology of bounds for resource constrained deployments.
  arXiv  Detail & Related papers  (2025-09-27T22:31:24Z)
• Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
  We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
  arXiv  Detail & Related papers  (2025-09-26T23:40:47Z)
• Lightweight Federated Learning over Wireless Edge Networks [83.4818741890634]
  Federated (FL) is an alternative at network edge, but an alternative in wireless networks.<n>We derive a closed-form expression FL convergence gap transmission power, model pruning error, and quantization.<n> LTFL outperforms state-the-art schemes in experiments on real-world datasets.
  arXiv  Detail & Related papers  (2025-07-13T09:14:17Z)
• Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference [54.53508601749513]
  We propose a task-oriented feature compression (TOFC) method for multimodal understanding in a device-edge co-inference framework.<n>To enhance compression efficiency, multiple entropy models are adaptively selected based on the characteristics of the visual features.<n>Results show that TOFC achieves up to 52% reduction in data transmission overhead and 63% reduction in system latency.
  arXiv  Detail & Related papers  (2025-03-17T08:37:22Z)
• Efficient Deployment of Large Language Models on Resource-constrained Devices [12.644230479753476]
  It is necessary to fine-tune Large Language Models (LLMs) on resource-constrained devices for various downstream tasks.<n>FedSpine is a framework that combines Efficient Fine-Tuning (PEFT) with structured pruning for efficient deployment of LLMs on resource-constrained devices.<n>We show that FedSpine can speed up fine-tuning by 1.4times$$$times and improve final accuracy by 0.4%-4.5% under the same sparsity level compared to other baselines.
  arXiv  Detail & Related papers  (2025-01-05T04:38:11Z)
• Hierarchical Federated Learning in Wireless Networks: Pruning Tackles Bandwidth Scarcity and System Heterogeneity [32.321021292376315]
  We propose a pruning-enabled hierarchical federated learning (PHFL) in heterogeneous networks (HetNets) We first derive an upper bound of the convergence rate that clearly demonstrates the impact of the model pruning and wireless communications. We validate the effectiveness of our proposed PHFL algorithm in terms of test accuracy, wall clock time, energy consumption and bandwidth requirement.
  arXiv  Detail & Related papers  (2023-08-03T07:03:33Z)
• Adaptive Federated Pruning in Hierarchical Wireless Networks [69.6417645730093]
  Federated Learning (FL) is a privacy-preserving distributed learning framework where a server aggregates models updated by multiple devices without accessing their private datasets. In this paper, we introduce model pruning for HFL in wireless networks to reduce the neural network scale. We show that our proposed HFL with model pruning achieves similar learning accuracy compared with the HFL without model pruning and reduces about 50 percent communication cost.
  arXiv  Detail & Related papers  (2023-05-15T22:04:49Z)
• Quantized Federated Learning under Transmission Delay and Outage Constraints [30.892724364965005]
  Federated learning is a viable distributed learning paradigm which trains a machine learning model collaboratively with massive mobile devices in the wireless edge. In practical systems with limited radio resources, transmission of a large number of model parameters inevitably suffers from quantization errors (QE) and transmission outage (TO) We propose a robust FL scheme, named FedTOE, which performs joint allocation of wireless resources and quantization bits across the clients to minimize the QE while making the clients have the same TO probability.
  arXiv  Detail & Related papers  (2021-06-17T11:29:12Z)

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.