Search:
Match:
2 results
Research Paper#Federated Learning, Clustering, Privacy-Preserving Machine Learning🔬 ResearchAnalyzed: Jan 3, 2026 19:28

Federated Multi-Task Clustering for Decentralized Data

Published:Dec 28, 2025 12:02
1 min read
ArXiv

Analysis

This paper addresses the challenge of clustering in decentralized environments, where data privacy is a concern. It proposes a novel framework, FMTC, that combines personalized clustering models for heterogeneous clients with a server-side module to capture shared knowledge. The use of a parameterized mapping model avoids reliance on unreliable pseudo-labels, and the low-rank regularization on a tensor of client models is a key innovation. The paper's contribution lies in its ability to perform effective clustering while preserving privacy and accounting for data heterogeneity in a federated setting. The proposed algorithm, based on ADMM, is also a significant contribution.
Reference

“The FMTC framework significantly outperforms various baseline and state-of-the-art federated clustering algorithms.”

PermalinkArXiv
Research Paper#Computational Fluid Dynamics, Porous Media, Multiphase Flow🔬 ResearchAnalyzed: Jan 4, 2026 00:15

Enhanced Models for Fluid Flow in Porous Structures

Published:Dec 25, 2025 14:45
1 min read
ArXiv

Analysis

This paper addresses the challenge of simulating multi-component fluid flow in complex porous structures, particularly when computational resolution is limited. The authors improve upon existing models by enhancing the handling of unresolved regions, improving interface dynamics, and incorporating detailed fluid behavior. The focus on practical rock geometries and validation through benchmark tests suggests a practical application of the research.
Reference

“The study introduces controllable surface tension in a pseudo-potential lattice Boltzmann model while keeping interface thickness and spurious currents constant, improving interface dynamics resolution.”

PermalinkArXiv