aiqbench analysis
This paper addresses the fragmentation bottleneck in federated clustering by introducing a one-shot hierarchical framework that stitches local clusterlets into a global distribution without multi-round communication. The approach leverages dynamic parameter-interleaving to scramble transmission trajectories, thereby mitigating privacy risks while reconstructing coherent hierarchies from heterogeneous Non-IID data. Extensive experiments on real benchmarks validate its ability to bridge granularity gaps and minimize exposure through anonymized informative updates.
Stitch the Fragments: One-Shot Hierarchical Federated Clustering
arXiv:2601.06404v2 Announce Type: replace Abstract: Federated Clustering (FC) faces a critical bottleneck in real-world scenarios, i.e., global clusters are rarely intact, often fragmenting into incomplete, multi-granular unlabeled ``clusterlets'' distributed across Non-IID clients. Although hierarchical clustering is theoretically well-suited to model such nested distributions, its recursive nature strictly relies on multi-round communication, introducing prohibitive computational overhead and severe privacy vulnerabilities. This paper, therefore, proposes a novel one-shot hierarchical federated clustering framework designed to seamlessly ``stitch'' the fragmented local clusterlets into a holistic global distribution. Our approach enables clients to perform autonomous fine-grained distribution exploration, uploading prototype-level knowledge via a dynamic parameter-interleaving mechanism to scramble transmission trajectories, which effectively prevents the server from tracing individual client data distributions. Subsequently, a multi-granular learning mechanism at the server fuses these granularly inconsistent local clusterlets, reconstructing a coherent global hierarchy for ultimate clustering. Extensive experiments on real benchmark datasets illustrate the superiority of the proposed approach, which effectively bridges the granularity gap among heterogeneous clients while minimizing privacy exposure risks via anonymized informative one-shot communication.
Abstract:Federated Clustering (FC) faces a critical bottleneck in real-world scenarios, i.e., global clusters are rarely intact, often fragmenting into incomplete, multi-granular unlabeled ``clusterlets'' distributed across Non-IID clients. Although hierarchical clustering is theoretically well-suited to model such nested distributions, its recursive nature strictly relies on multi-round communication, introducing prohibitive computational overhead and severe privacy vulnerabilities. This paper, therefore, proposes a novel one-shot hierarchical federated clustering framework designed to seamlessly ``stitch'' the fragmented local clusterlets into a holistic global distribution. Our approach enables clients to perform autonomous fine-grained distribution exploration, uploading prototype-level knowledge via a dynamic parameter-interleaving mechanism to scramble transmission trajectories, which effectively prevents the server from tracing individual client data distributions. Subsequently, a multi-granular learning mechanism at the server fuses these granularly inconsistent local clusterlets, reconstructing a coherent global hierarchy for ultimate clustering. Extensive experiments on real benchmark datasets illustrate the superiority of the proposed approach, which effectively bridges the granularity gap among heterogeneous clients while minimizing privacy exposure risks via anonymized informative one-shot communication.
Machine Learning (cs.LG)
arXiv:2601.06404 [cs.LG]
(or arXiv:2601.06404v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2601.06404 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 257 words
Related coverage
News
Quantum Computing Report · Jul 25, 2026
FedChronos: Federated Fine-Tuning of Time-Series Foundation Models for Privacy-Preserving Commodity Price Forecasting
arXiv · Aug 4, 2026
Mitigating Heterogeneity-Induced Drift in Hierarchical Sign-Based Federated Learning
arXiv · Jun 15, 2026
World Models and Yann LeCun’s Bet Against Large Language Models
Quantum Zeitgeist · Jul 17, 2026