An Experience Report on Regression-Free Repair of Deep Neural Network Model
This addresses the challenge of regression-free updates for DNNs in security-critical applications, but it is incremental as it builds on existing repair techniques.
The paper tackled the problem of updating deep neural networks in high-reliability industrial systems while minimizing regressions, and achieved suppression of regression for a specific class in a car image dataset by customizing the objective function based on NeuRecover.
Systems based on Deep Neural Networks (DNNs) are increasingly being used in industry. In the process of system operation, DNNs need to be updated in order to improve their performance. When updating DNNs, systems used in companies that require high reliability must have as few regressions as possible. Since the update of DNNs has a data-driven nature, it is difficult to suppress regressions as expected by developers. This paper identifies the requirements for DNN updating in industry and presents a case study using techniques to meet those requirements. In the case study, we worked on satisfying the requirement to update models trained on car images collected in Fujitsu assuming security applications without regression for a specific class. We were able to suppress regression by customizing the objective function based on NeuRecover, a DNN repair technique. Moreover, we discuss some of the challenges identified in the case study.