Privacy-Preserving Knowledge Transfer with Bootstrap Aggregation of Teacher Ensembles
- ORNL
- University of Kentucky
- LSUHSC-Louisiana Tumor Registry
- Rutgers Cancer Institute of New Jersey
- University of Utah
- National Cancer Institute, Bethesda, MD
There is a need to transfer knowledge among institutions and organizations to save effort in annotation and labeling or in enhancing task performance. However, knowledge transfer is difficult because of restrictions that are in place to ensure data security and privacy. Institutions are not allowed to exchange data or perform any activity that may expose personal information. With the leverage of a differential privacy algorithm in a high-performance computing environment, we propose a new training protocol, Bootstrap Aggregation of Teacher Ensembles (BATE), which is applicable to various types of machine learning models. The BATE algorithm is based on and provides enhancements to the PATE algorithm, maintaining competitive task performance scores on complex datasets with underrepresented class labels.We conducted a proof-of-the-concept study of the information extraction from cancer pathology report data from four cancer registries and performed comparisons between four scenarios: no collaboration, no privacy-preserving collaboration, the PATE algorithm, and the proposed BATE algorithm. The results showed that the BATE algorithm maintained competitive macro-averaged F1 scores, demonstrating that the suggested algorithm is an effective yet privacy-preserving method for machine learning and deep learning solutions.
- Research Organization:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 1771902
- Resource Relation:
- Journal Volume: 12633; Conference: International Conference on Very Large Data Bases (VLDB) - Tokyo, , Japan - 8/31/2020 8:00:00 AM-9/4/2020 8:00:00 AM
- Country of Publication:
- United States
- Language:
- English
Similar Records
Adversarial Training for Privacy-Preserving Deep Learning Model Distribution
Considerations for using Privacy Preserving Machine Learning Techniques for Safeguards