mlsanityData to 14 Oct 2026

Parameter-Efficient and Personalized Federated Training of Generative Models at the Edge

arXiv 2511.11585 ↗First posted 11 Oct 2025cs.LG cs.DCcited by 0

On the map: Diffusion models → Robustness, privacy and adversarial aspects

Abstract (arXiv)

Large generative models (for example, language and diffusion models) enable high-quality text and image synthesis but are hard to train or adapt in cross-device federated settings due to heavy computation and communication and statistical/system heterogeneity. We propose FedGen-Edge, a framework that decouples a frozen, pre-trained global backbone from lightweight client-side adapters and federates only the adapters. Using Low-Rank Adaptation (LoRA) constrains client updates to a compact subspace, which reduces uplink traffic by more than 99 percent versus full-model FedAvg, stabilizes aggregation under non-IID data, and naturally supports personalization because each client can keep a locally tuned adapter. On language modeling (PTB) and image generation (CIFAR-10), FedGen-Edge achieves lower perplexity/FID and faster convergence than strong baselines while retaining a simple FedAvg-style server. A brief ablation shows diminishing returns beyond moderate LoRA rank and a trade-off between local epochs and client drift. FedGen-Edge offers a practical path toward privacy-preserving, resource-aware, and personalized generative AI on heterogeneous edge devices.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 33 of its 66 references that are in the map. First posted on arXiv 11 Oct 2025.

Builds on

33 of 66 references.

References · 33

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  3. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  4. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2019Deep Leakage from Gradientscited by 1,021
  7. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  8. 2018How To Backdoor Federated Learningcited by 765
  9. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  10. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  11. 2019Federated Learning with Personalization Layerscited by 541
  12. 2021Towards Personalized Federated Learningcited by 464
21 more
  1. 2019Agnostic Federated Learningcited by 456
  2. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 455
  3. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 395
  4. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 383
  5. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227
  6. 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 155
  7. 2019Federated Learning for Wireless Communications: Motivation, Opportunities and Challengescited by 129
  8. 2021Federated Unlearning via Class-Discriminative Pruningcited by 115
  9. 2020Federated Unsupervised Representation Learningcited by 93
  10. 2022FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learningcited by 91
  11. 2018A General Approach to Adding Differential Privacy to Iterative Training Procedurescited by 84
  12. 2025Learning from Heterogeneity: Generalizing Dynamic Facial Expression Recognition via Distributionally Robust Optimizationcited by 19
  13. 2024WiOpen: A Robust Wi-Fi-based Open-set Gesture Recognition Frameworkcited by 16
  14. 2023ReSup: Reliable Label Noise Suppression for Facial Expression Recognitioncited by 14
  15. 2024Unified Static and Dynamic Network: Efficient Temporal Filtering for Video Groundingcited by 12
  16. 2025FedQuad: Adaptive Layer-wise LoRA Deployment and Activation Quantization for Federated Fine-Tuningcited by 10
  17. 2025Accelerating Mixture-of-Expert Inference with Adaptive Expert Split Mechanismcited by 9
  18. 2022FedFormer: Contextual Federation with Attention in Reinforcement Learningcited by 8
  19. 2024Accelerating End-Cloud Collaborative Inference via Near Bubble-free Pipeline Optimizationcited by 7
  20. 2025Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuningcited by 7
  21. 2025Towards Communication-Efficient Decentralized Federated Graph Learning over Non-IID Datacited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Edge-Assisted Collaborative Fine-Tuning for Multi-User Personalized Artificial Intelligence Generated Content (AIGC)
  2. 2025FedVLM: Scalable Personalized Vision-Language Models through Federated Learning
  3. 2025FedALT: Federated Fine-Tuning through Adaptive Local Training with Rest-of-World LoRA
  4. 2024FLoRA: Enhancing Vision-Language Models with Parameter-Efficient Federated Learning
  5. 2024Stable Diffusion-based Data Augmentation for Federated Learning with Non-IID Data
  6. 2026Concordia: Self-Improving Synthetic Tables for Federated LLMs
  7. 2025FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updates
  8. 2026AlignFed: Alignment-Aware Asynchronous Federated Fine-Tuning for Large Language Models in Heterogeneous Edge Environments