methodology-11

Federated Unsupervised Learning

3260 papers • 126 benchmarks • 313 datasets

Federated unsupervised learning trains models from decentralized data that have no labels.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in federated-unsupervised-learning-11

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find federated-unsupervised-learning-11 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Collaborative Unsupervised Visual Representation Learning from Decentralized Data

Shuai Yi, Weiming Zhuang, Xin Gan, Yonggang Wen, Shuai Zhang•Fri Aug 13 2021

This work proposes a novel federated unsupervised learning framework, FedU, which outperforms training with only one party by over 5% and other methods by over 14% in linear and semi-supervised evaluation on non-IID data.

117

Content

0

Paper Graph

Divergence-aware Federated Self-Supervised Learning

Weiming Zhuang, Yonggang Wen, Shuai Zhang•Fri Apr 08 2022

This study introduces a generalized FedSSL framework that embraces existing SSL methods based on Siamese networks, and proposes a new approach for model update, Federated Divergence-aware Exponential Moving Average update (FedEMA), which outperforms existing methods by 3-4% on linear evaluation.

119 0

Paper Graph

Hierarchical Bayes Approach to Personalized Federated Unsupervised Learning

Kaan Ozkara, Bruce Huang, Ruida Zhou, S. Diggavi•Sun Feb 18 2024

This work develops adaptive algorithms that discover the balance between using limited local data and collaborative information, and develops a theoretical framework for personalized diffusion models, which shows the benefits of collaboration even under heterogeneity.

1 0

Paper Graph

Adding a benchmark result helps the community track progress.