CSC, Riken working together on privacy-preserving machine learning models

20 Jun 2024 | Network Updates | Update from CSC – IT CENTER FOR SCIENCE
These updates are republished press releases and communications from members of the Science|Business Network

Professor Antti Honkela from the University of Helsinki, Finland, and Professor Samuel Kaski from Aalto University, Finland, and University of Manchester, UK, are part of the Finnish Center for Artificial Intelligence FCAI. Their Japanese collaboration partner is from RIKEN, which hosts Japan’s national flagship supercomputer Fugaku:

“We’re collaborating with Professor Jun Sakuma from RIKEN and Tokyo Institute of Technology. The collaboration builds on earlier collaboration on privacy-preserving machine learning with Japanese researchers.”

Developing a tool for private machine learning models

The project of Professors Honkela and Kaski naturally relates to artificial intelligence, more specifically to privacy-preserving machine learning.

“Machine learning models have been shown to be prone to memorising their training data. This can cause problems if the training data contains personal data or other sensitive information, such as health data, and as the model is subsequently made available to others, they may be able to recover the sensitive data,” the researchers explain.

The project aims to aid this conundrum:

“The memorization can be avoided by employing differential privacy in model training. Unfortunately this can reduce the accuracy of the model. Careful adjustment of the training process can minimize the loss of accuracy, but this can be computationally expensive and requires expertise. The ultimate aim of our project is to develop an artificial intelligence (AI) assistant for differentially private machine learning. The assistant will allow less experienced users to train strong models without excessive computation.”

AI research requires powerful platforms

LUMI as one of the world-leading AI platforms plays a large role also in this project.

“We use LUMI to train many models for different machine learning tasks. Collecting this information allows us to distill the knowledge of how to perform effective training in different tasks and ultimately train our AI assistant. The assistant will be developed iteratively such that its capabilities will increase as the project will progress,” Professors Honkela and Kaski describe.

They underline the importance of suitable platforms for artificial intelligence research in general:

“Research in machine learning and AI has become extremely compute-intensive during the past few years. World-class computational research infrastructure allows us to work on state-of-the-art models and problems that are relevant to users of the methods, rather than smaller inferior models that are computationally cheaper but usually not practically relevant.”

This article was first published on 17 June by CSC - IT Science for Science

Never miss an update from Science|Business:   Newsletter sign-up