mlsanityData to 14 Oct 2026

One-Shot Federated Clustering of Non-Independent Completely Distributed Data

arXiv 2601.17512 ↗First posted 24 Jan 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) that extracts data knowledge while protecting the privacy of multiple clients has achieved remarkable results in distributed privacy-preserving IoT systems, including smart traffic flow monitoring, smart grid load balancing, and so on. Since most data collected from edge devices are unlabeled, unsupervised Federated Clustering (FC) is becoming increasingly popular for exploring pattern knowledge from complex distributed data. However, due to the lack of label guidance, the common Non-Independent and Identically Distributed (Non-IID) issue of clients have greatly challenged FC by posing the following problems: How to fuse pattern knowledge (i.e., cluster distribution) from Non-IID clients; How are the cluster distributions among clients related; and How does this relationship connect with the global knowledge fusion? In this paper, a more tricky but overlooked phenomenon in Non-IID is revealed, which bottlenecks the clustering performance of the existing FC approaches. That is, different clients could fragment a cluster, and accordingly, a more generalized Non-IID concept, i.e., Non-ICD (Non-Independent Completely Distributed), is derived. To tackle the above FC challenges, a new framework named GOLD (Global Oriented Local Distribution Learning) is proposed. GOLD first finely explores the potential incomplete local cluster distributions of clients, then uploads the distribution summarization to the server for global fusion, and finally performs local cluster enhancement under the guidance of the global distribution. Extensive experiments, including significance tests, ablation studies, scalability evaluations, qualitative results, etc., have been conducted to show the superiority of GOLD.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 60 references that are in the map. First posted on arXiv 24 Jan 2026.

Builds on

20 of 60 references.

References · 20

  1. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  2. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  3. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  4. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 374
  5. 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 223
  6. 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 156
  7. 2021Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillationcited by 134
  8. 2021Heterogeneity for the Win: One-Shot Federated Clusteringcited by 87
  9. 2023Federated Continual Learning via Knowledge Fusion: A Surveycited by 53
  10. 2023Spatio-temporal Diffusion Point Processescited by 52
  11. 2020Multimodal Generative Learning Utilizing Jensen-Shannon-Divergencecited by 48
  12. 2022Towards Federated Clustering: A Federated Fuzzy c-Means Algorithm (FFCM)cited by 30
8 more
  1. 2022Machine Unlearning of Federated Clusterscited by 22
  2. 2022FedForgery: Generalized Face Forgery Detection with Residual Federated Learningcited by 12
  3. 2024Asynchronous Federated Clustering with Unknown Number of Clusterscited by 11
  4. 2024Learning Self-Growth Maps for Fast and Accurate Imbalanced Streaming Data Clusteringcited by 9
  5. 2023Differentially Private Federated Clustering over Non-IID Datacited by 7
  6. 2023Anomaly Detection with Score Distribution Discriminationcited by 7
  7. 2026Robust Categorical Data Clustering Guided by Multi-Granular Competitive Learningcited by 7
  8. 2020Federated Matrix Factorization: Algorithm Design and Application to Data Clusteringcited by 5

Built on by

Not cited yet.