Federated t-SNE and UMAP for Distributed Data Visualization

Федеративные t-SNE и UMAP для визуализации распределенных данных
Dong Qiao, Jicong Fan, Xinxian Ma
2025-04-11

UMAPdifferential privacyfederated learningfederated spectral clusteringt-SNE
High-dimensional data visualization is crucial in big data era and these techniques such as t-SNE and UMAP have been widely used in science and engineering. Big data, however, is often distributed across multiple data centers and subject to security and privacy concerns, which leads to difficulties for the standard algorithms of t-SNE and UMAP. To tackle the challenge, this work proposes Fed-tSNE and Fed-UMAP, which provide high-dimensional data visualization under the framework of federated learning, without exchanging data across clients or sending data to the central server. The main idea of Fed-tSNE and Fed-UMAP is implicitly learning the distribution information of data in a manner of federated learning and then estimating the global distance matrix for t-SNE and UMAP. To further enhance the protection of data privacy, we propose Fed-tSNE+ and Fed-UMAP+. We also extend our idea to federated spectral clustering, yielding algorithms of clustering distributed data. In addition to these new algorithms, we offer theoretical guarantees of distance and similarity estimation and analyze the property of differential privacy. Experiments on multiple datasets demonstrate that, compared to the original algorithms, the accuracy drops of our federated algorithms are tiny.
1
Fed-tSNE and Fed-UMAP enable distributed high-dimensional visualization without exchanging client data or sending raw data to a central server.
2
Fed-tSNE+ and Fed-UMAP+ are introduced to provide enhanced data-privacy protection.
3
The federated approach is extended to spectral clustering, enabling clustering of data distributed across multiple clients.
4
The methods implicitly learn global data-distribution information through federated learning and estimate the global distance matrix required by t-SNE and UMAP.
5
Theoretical guarantees cover distance and similarity estimation, while experiments on multiple datasets show only tiny accuracy drops compared with the original algorithms.

distributed high-dimensional data across multiple data centers/clients

privacy-preserving federated visualization and clustering, including global distance/similarity estimation and accuracy under distributed data constraints

Publication Details
Publication Date
2025-04-11
Journal
Publisher
ISSN
Cited by
7
Access Type
Author Information
Authors
Dong Qiao
Jicong Fan
Xinxian Ma
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%