Osmotic Learning: A Self-Supervised Paradigm for Decentralized Contextual Data Representation
By: Mario Colosi , Reza Farahani , Maria Fazio and more
Potential Business Impact:
Finds hidden patterns in shared computer information.
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.
Similar Papers
OASIS: Open-world Adaptive Self-supervised and Imbalanced-aware System
Machine Learning (CS)
Teaches computers to learn from messy, incomplete data.
Self-organizing maps for water quality assessment in reservoirs and lakes: A systematic literature review
Machine Learning (CS)
Finds hidden lake problems from lots of data.
Learning to Retrieve for Environmental Knowledge Discovery: An Augmentation-Adaptive Self-Supervised Learning Framework
Machine Learning (CS)
Helps predict water quality with less data.