Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling

2022/10/23 by Junyuan Hong, Hong, Junyuan, Lingjuan Lyu +5 · 1 citation
Computer Science · Medicine · #Privacy-Preserving Technologies in Data #COVID-19 diagnosis using AI #Domain Adaptation and Few-Shot Learning

paper · doi:10.48550/arxiv.2210.12575

Abstract

, which is a massive dataset collected from public and heterogeneous sources (e.g., Internet images). We develop a novel strategy called Efficient Collaborative Open-source Sampling (ECOS) to construct a proximal proxy dataset from open-source data for cloud training, in lieu of client data. ECOS probes open-source data on the cloud server to sense the distribution of client data via a communication- and computation-efficient sampling process, which only communicates a few compressed public features and client scalar responses. Extensive empirical studies show that the proposed ECOS improves the quality of automated client labeling, model compression, and label outsourcing when applied in various learning scenarios.

Cited by

• The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor Attacks

Related

• Machine Learning and Cloud Computing: Survey of Distributed and SaaS Solutions
• How Can We Train Deep Learning Models Across Clouds and Continents? An Experimental Study
• Positive-Unlabeled Compression on the Cloud
• DC-CCL: Device-Cloud Collaborative Controlled Learning for Large Vision Models
• Accelerated Cloud for Artificial Intelligence (ACAI)