Global Balanced Experts for Federated Long-Tailed Learning

[PDF] arxiv.org

Addressing Skewed Heterogeneity via Federated Prototype Rectification With Personalization

S Guo, H Wang, S Lin, Z Kou… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Federated learning (FL) is an efficient framework designed to facilitate collaborative model
training across multiple distributed devices while preserving user data privacy. A significant …
相关文章 所有 4 个版本
[PDF] arxiv.org

Bridging data islands: Geographic heterogeneity-aware federated learning for collaborative remote sensing semantic segmentation

J Tan, Y Li, SA Bartalev, B Dang, W Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Remote sensing semantic segmentation (RSS) is an essential task in Earth Observation
missions. Due to data privacy concerns, high-quality remote sensing images with …
被引用次数：1 相关文章 所有 2 个版本

Personalized Federated Learning on long-tailed data via knowledge distillation and generated features

F Lv, P Qian, Y Lu, H Wang - Pattern Recognition Letters, 2024 - Elsevier
Abstract Personalized Federated Learning (PFL) offers a novel paradigm for distributed
learning, which aims to learn a personalized model for each client through collaborative …
相关文章

FedCRAC: Improving Federated Classification Performance on Long-Tailed Data Via Classifier Representation Adjustment and Calibration

X Li, S Sun, M Liu, J Ren, X Jiang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Federated learning has been a popular distributed training paradigm that enables to train a
shared model with data privacy protection. However, non-Independent Identically …
相关文章 所有 2 个版本
[PDF] arxiv.org

Not all Minorities are Equal: Empty-Class-Aware Distillation for Heterogeneous Federated Learning

K Guo, Y Ding, J Liang, R He, Z Wang, T Tan - arXiv preprint arXiv …, 2024 - arxiv.org
Data heterogeneity, characterized by disparities in local data distribution across clients,
poses a significant challenge in federated learning. Substantial efforts have been devoted to …
被引用次数：2 相关文章 所有 2 个版本
[PDF] arxiv.org

Personalized Federated Learning on Heterogeneous and Long-Tailed Data via Expert Collaborative Learning

F Lv, X Shang, Y Zhou, Y Zhang, M Li, Y Lu - arXiv preprint arXiv …, 2024 - arxiv.org
Personalized Federated Learning (PFL) aims to acquire customized models for each client
without disclosing raw data by leveraging the collective knowledge of distributed clients …
相关文章 所有 2 个版本

Medi: Multi-Expert with Extra Data Introduction for Long-Tailed Classification

C Deng, L Ji, B Li, L Wang, J Zhang - Available at SSRN 4873502 - papers.ssrn.com
Constrained by the scarcity of data on tail classes, recent studies have proposed introducing
extra data to tackle the long-tailed classification (LTC) problem. However, existing extra data …
相关文章