Loading [a11y]/accessibility-menu.js
Repairing DNN Architecture: Are We There Yet? | IEEE Conference Publication | IEEE Xplore

Repairing DNN Architecture: Are We There Yet?


Abstract:

As Deep Neural Networks (DNNs) are rapidly being adopted within large software systems, software developers are increasingly required to design, train, and deploy such mo...Show More

Abstract:

As Deep Neural Networks (DNNs) are rapidly being adopted within large software systems, software developers are increasingly required to design, train, and deploy such models into the systems they develop. Consequently, testing and improving the robustness of these models have received a lot of attention lately. However, relatively little effort has been made to address the difficulties developers experience when designing and training such models: if the evaluation of a model shows poor performance after the initial training, what should the developer change? We survey and evaluate existing state-of-the-art techniques that can be used to repair model performance, using a benchmark of both real-world mistakes developers made while designing DNN models and artificial faulty models generated by mutating the model code. The empirical evaluation shows that random baseline is comparable with or sometimes outperforms existing state-of-the-art techniques. However, for larger and more complicated models, all repair techniques fail to find fixes. Our findings call for further research to develop more sophisticated techniques for Deep Learning repair.
Date of Conference: 16-20 April 2023
Date Added to IEEE Xplore: 26 May 2023
ISBN Information:
Print on Demand(PoD) ISSN: 2159-4848
Conference Location: Dublin, Ireland

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.