无需交换原始数据，通过自监督学习挖掘分布式数据中的隐含关系。
Osmotic Learning: A Self-Supervised Paradigm for Decentralized Contextual Data Representation
- 利用渗透机制融合上下文信息，生成紧凑且丰富的数据表示
- 在结构化数据上实现超过0.99的局部对齐准确率，保持上下文完整性
- 适合隐私敏感场景下的分布式建模，如医疗或金融系统
特定上下文中的数据远超孤立解读的意义。在分布式系统中，相互依赖的数据源揭示隐藏关系与潜在结构，为诸多应用提供宝贵信息。本文提出自监督分布式学习范式Osmotic Learning（OSM-L），旨在从分散数据中挖掘高层级潜在知识。其核心是渗透过程，通过提取上下文信息生成密集紧凑的表示，避免实体间原始数据交换。OSM-L迭代对齐本地数据表示，促进信息扩散并收敛至动态平衡，捕捉上下文模式。训练期间还可识别相关数据组，充当去中心化聚类机制。实验表明，该方法在结构化数据集上具备收敛性与表征能力，局部信息对齐准确率超过0.99，同时保持上下文完整性。
原文摘要 · Abstract (English)
Data within a specific context gains deeper significance beyond its isolated interpretation. In distributed systems, interdependent data sources reveal hidden relationships and latent structures, representing valuable information for many applications. This paper introduces Osmotic Learning (OSM-L), a self-supervised distributed learning paradigm designed to uncover higher-level latent knowledge from distributed data. The core of OSM-L is osmosis, a process that synthesizes dense and compact representation by extracting contextual information, eliminating the need for raw data exchange between distributed entities. OSM-L iteratively aligns local data representations, enabling information diffusion and convergence into a dynamic equilibrium that captures contextual patterns. During training, it also identifies correlated data groups, functioning as a decentralized clustering mechanism. Experimental results confirm OSM-L's convergence and representation capabilities on structured datasets, achieving over 0.99 accuracy in local information alignment while preserving contextual integrity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。