FedRef: Communication-Efficient Bayesian Fine-Tuning using a Reference Model

• URL: http://arxiv.org/abs/2506.23210v3
• Date: Wed, 05 Nov 2025 00:27:36 GMT
• Title: FedRef: Communication-Efficient Bayesian Fine-Tuning using a Reference Model
• Authors: Taehwan Yoon, Bongjun Choi, Wesley De Neve,
• Abstract summary: Federated learning (FL) collaboratively trains artificial intelligence (AI) models to ensure user data privacy.<n>Previous studies have proposed model optimization, fine-tuning, and personalization to achieve improved model performance.<n>We propose a reference model-based fine-tuning method for federated learning that overcomes catastrophic forgetting in each round.
• Score: 0.7100520098029438
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Federated learning (FL) collaboratively trains artificial intelligence (AI) models to ensure user data privacy. Sharing only model updates generated from local training on client data with the server enhances user data privacy. However, model performance may suffer due to data and system heterogeneity among clients in FL scenarios. Previous studies have proposed model optimization, fine-tuning, and personalization to achieve improved model performance. Despite these efforts, models resulting from FL scenarios often exhibit catastrophic forgetting, which increases the communication and computational costs of clients for model optimization and raises energy consumption. To address these challenges, we propose a reference model-based fine-tuning method for federated learning that overcomes catastrophic forgetting in each round. Our method is derived from Bayesian parameter-efficient transfer learning and includes an proximal term. It employs a reference model that incorporates previous model parameters and reviews previous global features in the model optimization step to mitigate catastrophic forgetting. As a result, our method achieves higher model performance and lower communication and computational costs for clients than existing methods.

Related papers

• Boosting Generalization Performance in Model-Heterogeneous Federated Learning Using Variational Transposed Convolution [0.27309692684728615]
  Federated learning (FL) is a pioneering machine learning paradigm that enables distributed clients to process local data effectively.<n>Traditional model-homogeneous approaches mainly involve debiasing the local training procedures with regularization or dynamically adjusting client weights in aggregation.<n>We propose a model-heterogeneous FL framework that can improve clients' generalization performance over unseen data without model aggregation.
  arXiv  Detail & Related papers  (2025-08-03T08:55:18Z)
• Intention-Conditioned Flow Occupancy Models [69.79049994662591]
  Large-scale pre-training has fundamentally changed how machine learning research is done today.<n>Applying this same framework to reinforcement learning is appealing because it offers compelling avenues for addressing core challenges in RL.<n>Recent advances in generative AI have provided new tools for modeling highly complex distributions.
  arXiv  Detail & Related papers  (2025-06-10T15:27:46Z)
• Pre-training for Recommendation Unlearning [14.514770044236375]
  UnlearnRec is a model-agnostic pre-training paradigm that prepares systems for efficient unlearning operations.<n>Our method delivers exceptional unlearning effectiveness while providing more than 10x speedup compared to retraining approaches.
  arXiv  Detail & Related papers  (2025-05-28T17:57:11Z)
• Not All Clients Are Equal: Personalized Federated Learning on Heterogeneous Multi-Modal Clients [52.14230635007546]
  Foundation models have shown remarkable capabilities across diverse multi-modal tasks, but their centralized training raises privacy concerns and induces high transmission costs.<n>For the growing demand for personalizing AI models for different user purposes, personalized federated learning (PFL) has emerged.<n>PFL allows each client to leverage the knowledge of other clients for further adaptation to individual user preferences, again without the need to share data.
  arXiv  Detail & Related papers  (2025-05-20T09:17:07Z)
• Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient [9.519619751861333]
  We propose a state space model (SSM)-based world model, Drama, that achieves $O(n)$ memory and computational complexity.<n>We also introduce a novel sampling method to mitigate the suboptimality caused by an incorrect world model in the early training stages.<n>Drama is accessible and trainable on off-the-shelf hardware, such as a standard laptop.
  arXiv  Detail & Related papers  (2024-10-11T15:10:40Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment [65.15914284008973]
  We propose to leverage an Inverse Reinforcement Learning (IRL) technique to simultaneously build an reward model and a policy model. We show that the proposed algorithms converge to the stationary solutions of the IRL problem. Our results indicate that it is beneficial to leverage reward learning throughout the entire alignment process.
  arXiv  Detail & Related papers  (2024-05-28T07:11:05Z)
• An Aggregation-Free Federated Learning for Tackling Data Heterogeneity [50.44021981013037]
  Federated Learning (FL) relies on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models based on a global model aggregated by the server from the previous training round. We introduce FedAF, a novel aggregation-free FL algorithm.
  arXiv  Detail & Related papers  (2024-04-29T05:55:23Z)
• CoDream: Exchanging dreams instead of models for federated aggregation with heterogeneous models [8.85591781936764]
  We present a novel framework called CoDream, where clients collaboratively optimize randomly data. Our key insight is that jointly optimizing this data can effectively capture the properties of the global data distribution. We empirically validate CoDream on standard FL tasks, demonstrating competitive performance despite not sharing model parameters.
  arXiv  Detail & Related papers  (2024-02-25T03:07:32Z)
• Federated Learning with Projected Trajectory Regularization [65.6266768678291]
  Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients. We propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data issue.
  arXiv  Detail & Related papers  (2023-12-22T02:12:08Z)
• Federated Learning While Providing Model as a Service: Joint Training and Inference Optimization [30.305956110710266]
  Federated learning is beneficial for enabling the training of models across distributed clients. Existing work has overlooked the coexistence of model training and inference under clients' limited resources. This paper focuses on the joint optimization of model training and inference to maximize inference performance at clients.
  arXiv  Detail & Related papers  (2023-12-20T09:27:09Z)
• One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models [40.83058938096914]
  FedLMG is a one-shot Federated learning method with Local Model-Guided diffusion models.<n>Clients do not need access to any foundation models but only train and upload their local models.
  arXiv  Detail & Related papers  (2023-11-15T11:11:25Z)
• Fairer and More Accurate Tabular Models Through NAS [14.147928131445852]
  We propose using multi-objective Neural Architecture Search (NAS) and Hyperparameter Optimization (HPO) in the first application to the very challenging domain of tabular data. We show that models optimized solely for accuracy with NAS often fail to inherently address fairness concerns. We produce architectures that consistently dominate state-of-the-art bias mitigation methods either in fairness, accuracy or both.
  arXiv  Detail & Related papers  (2023-10-18T17:56:24Z)
• Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
  We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
  arXiv  Detail & Related papers  (2023-05-01T20:04:46Z)
• Dataless Knowledge Fusion by Merging Weights of Language Models [47.432215933099016]
  Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models.<n>This creates a barrier to fusing knowledge across individual models to yield a better single model.<n>We propose a dataless knowledge fusion method that merges models in their parameter space.
  arXiv  Detail & Related papers  (2022-12-19T20:46:43Z)
• HyperImpute: Generalized Iterative Imputation with Automatic Model Selection [77.86861638371926]
  We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models. We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
  arXiv  Detail & Related papers  (2022-06-15T19:10:35Z)
• Approximate Bayesian Optimisation for Neural Networks [6.921210544516486]
  A body of work has been done to automate machine learning algorithm to highlight the importance of model choice. The necessity to solve the analytical tractability and the computational feasibility in a idealistic fashion enables to ensure the efficiency and the applicability.
  arXiv  Detail & Related papers  (2021-08-27T19:03:32Z)
• Conservative Objective Models for Effective Offline Model-Based Optimization [78.19085445065845]
  Computational design problems arise in a number of settings, from synthetic biology to computer architectures. We propose a method that learns a model of the objective function that lower bounds the actual value of the ground-truth objective on out-of-distribution inputs. COMs are simple to implement and outperform a number of existing methods on a wide range of MBO problems.
  arXiv  Detail & Related papers  (2021-07-14T17:55:28Z)
• SCEI: A Smart-Contract Driven Edge Intelligence Framework for IoT Systems [15.796325306292134]
  Federated learning (FL) enables collaborative training of a shared model on edge devices while maintaining data privacy. Various personalized approaches have been proposed, but such approaches fail to handle underlying shifts in data distribution. This paper presents a dynamically optimized personal deep learning scheme based on blockchain and federated learning.
  arXiv  Detail & Related papers  (2021-03-12T02:57:05Z)
• A Bayesian Federated Learning Framework with Online Laplace Approximation [144.7345013348257]
  Federated learning allows multiple clients to collaboratively learn a globally shared model. We propose a novel FL framework that uses online Laplace approximation to approximate posteriors on both the client and server side. We achieve state-of-the-art results on several benchmarks, clearly demonstrating the advantages of the proposed method.
  arXiv  Detail & Related papers  (2021-02-03T08:36:58Z)
• Bayesian Optimization for Selecting Efficient Machine Learning Models [53.202224677485525]
  We present a unified Bayesian Optimization framework for jointly optimizing models for both prediction effectiveness and training efficiency. Experiments on model selection for recommendation tasks indicate models selected this way significantly improves model training efficiency.
  arXiv  Detail & Related papers  (2020-08-02T02:56:30Z)
• Model Fusion via Optimal Transport [64.13185244219353]
  We present a layer-wise model fusion algorithm for neural networks. We show that this can successfully yield "one-shot" knowledge transfer between neural networks trained on heterogeneous non-i.i.d. data.
  arXiv  Detail & Related papers  (2019-10-12T22:07:15Z)

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.