SplitNN-driven Vertical Partitioning
This work addresses data privacy and collaboration issues for institutions with vertically distributed features, but it is incremental as it builds on the existing SplitNN method.
The paper tackled the problem of training deep learning models on vertically partitioned data across institutions without sharing raw data or model details, and found that the proposed SplitNN-driven vertical partitioning configuration is flexible and allows various configurations to address specific challenges of vertically split datasets.
In this work, we introduce SplitNN-driven Vertical Partitioning, a configuration of a distributed deep learning method called SplitNN to facilitate learning from vertically distributed features. SplitNN does not share raw data or model details with collaborating institutions. The proposed configuration allows training among institutions holding diverse sources of data without the need of complex encryption algorithms or secure computation protocols. We evaluate several configurations to merge the outputs of the split models, and compare performance and resource efficiency. The method is flexible and allows many different configurations to tackle the specific challenges posed by vertically split datasets.