Unsupervised Federated Learning

Unsupervised federated learning (UFL) aims to collaboratively train machine learning models on decentralized, unlabeled data without compromising individual data privacy. Current research focuses on addressing challenges like data heterogeneity and representation inconsistencies across clients, employing techniques such as federated clustering, gradient alignment, and knowledge distillation within various model architectures including autoencoders, recurrent neural networks, and contrastive learning frameworks. This field is significant because it expands the applicability of federated learning to a wider range of real-world scenarios where labeled data is scarce or unavailable, enabling privacy-preserving analysis of distributed datasets in diverse applications.

Papers

August 20, 2024

Federated Clustering: An Unsupervised Cluster-Wise Training for Decentralized Data Distributions
Mirko Nardi, Lorenzo Valerio, Andrea Passarella
Decentralized Data Decentralized Machine Learning Federated Clustering Unsupervised Federated Learning

May 25, 2024

Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradients
Farhad Pourpanah, Mahdiyar Molahasani, Milad Soltany, Michael Greenspan, Ali Etemad
Federated Learning Domain Shift World Event Gradient Alignment Unsupervised Federated Learning Local Alignment

April 17, 2024

Lightweight Unsupervised Federated Learning with Pretrained Vision Language Model
Hao Yan, Yuhong Guo
Zero Shot Deep Model Unsupervised Federated Learning Lightweight Classifier

March 25, 2024

Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data
Xinting Liao, Weiming Liu, Chaochao Chen, Pengyang Zhou, Fengyuan Yu, Huabin Zhu, Binhui Yao, Tao Wang, Xiaolin Zheng, Yanchao Tan
Raw Data Unsupervised Learning Individual Representation Representation Space Unified Representation Representation Collapse Unsupervised Federated Learning

February 15, 2024

Smart Information Exchange for Unsupervised Federated Learning via Reinforcement Learning
Seohyun Lee, Anindya Bijoy Das, Satyavrat Wagle, Christopher G. Brinton
Reinforcement Learning Benchmark Datasets Information Transfer Unsupervised Federated Learning Decentralized Machine Device to Device

October 23, 2023

Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms
Ye Tian, Haolei Weng, Yang Feng
Unsupervised Learning Theoretical Understanding Finite Sample EM Algorithm Non Asymptotic Analysis Unsupervised Federated Learning

July 23, 2023

ProtoFL: Unsupervised Federated Learning via Prototypical Distillation
Hansol Kim, Youngjun Kwak, Minyoung Jung, Jinho Shin, Youngsung Kim, Changick Kim
Data Privacy One Class Classification Unsupervised Federated Learning One Class Classifier

May 24, 2023

Stochastic Unrolled Federated Learning
Samar Hadou, Navid NaderiAlizadeh, Alejandro Ribeiro
Gradient Descent Unsupervised Federated Learning Unrolled Optimization

September 9, 2022

Anomaly Detection through Unsupervised Federated Learning
Mirko Nardi, Lorenzo Valerio, Andrea Passarella
Anomaly Detection Inlier Classification Unsupervised Federated Learning

August 4, 2022

Embedding Alignment for Unsupervised Federated Learning via Smart Data Exchange
Satyavrat Wagle, Seyyedali Hosseinalipour, Naji Khosravan, Mung Chiang, Christopher G. Brinton
Contrastive Learning Latent Space Alignment Problem Ad Hoc Unsupervised Federated Learning

July 19, 2022

FedX: Unsupervised Federated Learning with Cross Knowledge Distillation
Sungwon Han, Sungwon Park, Fangzhao Wu, Sundong Kim, Chuhan Wu, Xing Xie, Meeyoung Cha
Contrastive Learning Knowledge Distillation Learning Framework Unsupervised Algorithm Unsupervised Federated Learning Unbiased SGG

July 2, 2022

Unsupervised Recurrent Federated Learning for Edge Popularity Prediction in Privacy-Preserving Mobile Edge Computing Networks
Chong Zheng, Shengheng Liu, Yongming Huang, Wei Zhang, Luxi Yang
Mobile Edge Computing Edge Network Mobile Edge Popularity Prediction Unsupervised Federated Learning Dynamic Content Popularity Content Popularity

May 31, 2022

FedWalk: Communication Efficient Federated Unsupervised Node Embedding with Differential Privacy
Qiying Pan, Yifei Zhu
Differential Privacy Graph Representation Unsupervised Federated Learning Visibility Graph

May 23, 2022

Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering
Ekdeep Singh Lubana, Chi Ian Tang, Fahim Kawsar, Robert P. Dick, Akhil Mathur
Federated Learning Generalization Capability Co Orchestration Federated Training Unsupervised Federated Learning Discriminative Clustering

April 7, 2022

Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
Nan Lu, Zhao Wang, Xiaoxiao Li, Gang Niu, Qi Dou, Masashi Sugiyama
Unsupervised Learning Unlabeled Data Client Model Unsupervised Federated Learning

March 3, 2022

Vertical Federated Principal Component Analysis and Its Kernel Extension on Feature-wise Distributed Data
Yiu-ming Cheung, Juyong Jiang, Feng Yu, Jian Lou
Raw Data Feature Wise Principal Component Analysis Kernel Extension Unsupervised Federated Learning Decentralized Topology

Unsupervised Federated Learning

Papers

Federated Clustering: An Unsupervised Cluster-Wise Training for Decentralized Data Distributions

Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradients

Lightweight Unsupervised Federated Learning with Pretrained Vision Language Model

Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data

Smart Information Exchange for Unsupervised Federated Learning via Reinforcement Learning

Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms

ProtoFL: Unsupervised Federated Learning via Prototypical Distillation

Stochastic Unrolled Federated Learning

Anomaly Detection through Unsupervised Federated Learning

Embedding Alignment for Unsupervised Federated Learning via Smart Data Exchange

FedX: Unsupervised Federated Learning with Cross Knowledge Distillation

Unsupervised Recurrent Federated Learning for Edge Popularity Prediction in Privacy-Preserving Mobile Edge Computing Networks

FedWalk: Communication Efficient Federated Unsupervised Node Embedding with Differential Privacy

Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering

Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients

Vertical Federated Principal Component Analysis and Its Kernel Extension on Feature-wise Distributed Data