Cultivating Privacy in Collaborative Data Sharing through Auto-encoder Latent Space Embeddings

Abstract

Ensuring privacy in machine learning through collaborative data sharing is imperative for organizations aiming to leverage collective data without compromising confidentiality. This becomes particularly crucial when sensitive information must be safeguarded throughout the entire machine learning process, spanning from model training to inference. This paper introduces a novel framework employing Representation Learning through autoencoders to produce privacy-preserving embedded data. Consequently, organizations can share these representations, fostering improved performance of machine learning models in scenarios involving multiple data sources for a unified predictive task downstream.