Repairing DNN Architecture: Are We There Yet?

January 27, 2023 Β· Declared Dead Β· πŸ› International Conference on Information Control Systems & Technologies

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Jinhan Kim, Nargiz Humbatova, Gunel Jahangirova, Paolo Tonella, Shin Yoo arXiv ID 2301.11568 Category cs.SE: Software Engineering Citations 15 Venue International Conference on Information Control Systems & Technologies Last Checked 4 months ago
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Software Engineering

Died the same way β€” πŸ‘» Ghosted