paper-with-me

홈 › Papers

Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Data

2024-05-10 · Rongyu Zhang, Yun Chen, Chenrui Wu, Fangxin Wang, Bo Li

Federated learning (FL) offers a privacy-centric distributed learning framework, enabling model training on individual clients and central aggregation without necessitating data exchange. Nonetheless, FL implementations often suffer from non-i.i.d. and long-tailed class distributions across mobile applications, e.g., autonomous vehicles, which leads models to overfitting as local training may converge to sub-optimal. In our study, we explore the impact of data heterogeneity on model bias and introduce an innovative personalized FL framework, Multi-level Personalized Federated Learning (MuPFL), which leverages the hierarchical architecture of FL to fully harness computational resources at various levels. This framework integrates three pivotal modules: Biased Activation Value Dropout (BAVD) to mitigate overfitting and accelerate training; Adaptive Cluster-based Model Update (ACMU) to refine local models ensuring coherent global aggregation; and Prior Knowledge-assisted Classifier Fine-tuning (PKCF) to bolster classification and personalize models in accord with skewed local data with shared knowledge. Extensive experiments on diverse real-world datasets for image classification and semantic segmentation validate that MuPFL consistently outperforms state-of-the-art baselines, even under extreme non-i.i.d. and long-tail conditions, which enhances accuracy by as much as 7.39% and accelerates training by up to 80% at most, marking significant advancements in both efficiency and effectiveness.

📄 PDF Abstract BibTeX arXiv:2405.06413

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous VehiclesFederated Learningimage-classificationImage ClassificationPersonalized Federated LearningSemantic Segmentation

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

pFedAFM: Adaptive Feature Mixture for Batch-Level Personalization in Heterogeneous Federated Learning

2024-04-27 · Liping Yi, Han Yu, Chao Ren, Heng Zhang 외

Model-heterogeneous personalized federated learning (MHPFL) enables FL clients to train structurally different personalized models on non-independent and identically distributed (non-IID) local data. Existing MHPFL metho…

Federated LearningPersonalized Federated LearningPrediction

pFedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated Learning

2024-02-02 · Liping Yi, Han Yu, Chao Ren, Heng Zhang 외

Federated learning (FL) has been widely adopted for collaborative training on decentralized data. However, it faces the challenges of data, system, and model heterogeneity. This has inspired the emergence of model-hetero…

Federated LearningMixture-of-ExpertsPersonalized Federated Learning

Row-wise Fusion Regularization: An Interpretable Personalized Federated Learning Framework in Large-Scale Scenarios

2025-10-16 · Runlin Zhou, Letian Li, Zemin Zheng arxiv

We study personalized federated learning for multivariate responses where client models are heterogeneous yet share variable-level structure. Existing entry-wise penalties ignore cross-response dependence, while matrix-w…

Personalized Federated Learning

Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning

2026-05-04 · Shihao Hou, Chikai Shang, Zhiheng Yang, Jiacheng Yang 외 arxiv

Personalized federated learning (PFL) with foundation models has emerged as a promising paradigm enabling clients to adapt to heterogeneous data distributions. However, real-world scenarios often face the co-occurrence o…

Personalized Federated Learning

Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA

2025-03-05 · Jie Hao, Yuman Wu, Ali Payani, Myungjin Lee 외

We study the task of personalized federated fine-tuning with heterogeneous data in the context of language models, where clients collaboratively fine-tune a language model (e.g., BERT, GPT) without sharing their local da…

Language ModelingLanguage ModellingNatural Language Understandingparameter-efficient fine-tuning