paper-with-me

Papers

Personalizing Low-Rank Bayesian Neural Networks Via Federated Learning

2024-10-18 · Boning Zhang, Dongzhu Liu, Osvaldo Simeone, Guanchu Wang, Dimitrios Pezaros, Guangxu Zhu

To support real-world decision-making, it is crucial for models to be well-calibrated, i.e., to assign reliable confidence estimates to their predictions. Uncertainty quantification is particularly important in personalized federated learning (PFL), as participating clients typically have small local datasets, making it difficult to unambiguously determine optimal model parameters. Bayesian PFL (BPFL) methods can potentially enhance calibration, but they often come with considerable computational and memory requirements due to the need to track the variances of all the individual model parameters. Furthermore, different clients may exhibit heterogeneous uncertainty levels owing to varying local dataset sizes and distributions. To address these challenges, we propose LR-BPFL, a novel BPFL method that learns a global deterministic model along with personalized low-rank Bayesian corrections. To tailor the local model to each client's inherent uncertainty level, LR-BPFL incorporates an adaptive rank selection mechanism. We evaluate LR-BPFL across a variety of datasets, demonstrating its advantages in terms of calibration, accuracy, as well as computational and memory requirements.

📄 PDF Abstract BibTeX arXiv:2410.14390

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingFederated LearningPersonalized Federated LearningUncertainty Quantification

Similar Papers 제목 키워드 기반

Bayesian Neural Network For Personalized Federated Learning Parameter Selection

2024-02-25 · Mengen Luo, Ercan Engin Kuruoglu

Federated learning's poor performance in the presence of heterogeneous data remains one of the most pressing issues in the field. Personalized federated learning departs from the conventional paradigm in which all client…

Federated LearningPersonalized Federated Learning

Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation

2026-06-07 · Xingyue Zhao, Wenke Huang, Linghao Zhuang, Haoran Wu 외 arxiv

Low-Rank Adaptation (LoRA) enables efficient federated fine-tuning of segmentation foundation models for medical imaging. However, most federated LoRA methods adopt a uniform aggregation rule, which breaks under the enco…

FedSPD: A Soft-clustering Approach for Personalized Decentralized Federated Learning

2024-10-24 · I-Cheng Lin, Osman Yagan, Carlee Joe-Wong

Federated learning has recently gained popularity as a framework for distributed clients to collaboratively train a machine learning model using local data. While traditional federated learning relies on a central server…

ClusteringFederated LearningPersonalized Federated Learning

Personalizing or Not: Dynamically Personalized Federated Learning with Incentives

2022-08-12 · Zichen Ma, Yu Lu, Wenye Li, Shuguang Cui

Personalized federated learning (FL) facilitates collaborations between multiple clients to learn personalized models without sharing private data. The mechanism mitigates the statistical heterogeneity commonly encounter…

Federated LearningPersonalized Federated Learning

Demonstration of Adapt4Me: An Uncertainty-Aware Authoring Environment for Personalizing Automatic Speech Recognition to Non-normative Speech

2026-03-20 · Niclas Pokel, Yiming Zhao, Pehuén Moure, Yingqiang Gao 외 arxiv

Personalizing Automatic Speech Recognition (ASR) for non-normative speech remains challenging because data collection is labor-intensive and model training is technically complex. To address these limitations, we propose…

Speech RecognitionActive Learning