On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “SplitNN”

SplitNN-driven Vertical Partitioningcs.LG

SplitNN-driven Vertical Partitioning enables distributed learning from diverse data sources.

problem Learning from vertically distributed features across institutions.

method A configuration of SplitNN that does not share raw data or model details.

result Flexibility in merging split model outputs and resource efficiency.

SplitNN Vertical Partitioning Distributed Learning Diverse Data Sources Resource Efficiency

2020-08-07abs ↗pdf ↗

Split learning for health: Distributed deep learning without sharing raw patient datacs.LG

Can health entities collaboratively train deep learning models without sharing sensitive raw data? This paper proposes several configurations of a distributed deep learning method called SplitNN to facilitate such collaborations. SplitNN does not share raw data or model details with collaborating institutions. The prop…

2018-12-03abs ↗pdf ↗