Operational Calibration: Debugging Confidence Errors for DNNs in the Field

October 06, 2019 Β· Declared Dead Β· πŸ› ESEC/SIGSOFT FSE

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

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Zenan Li, Xiaoxing Ma, Chang Xu, Jingwei Xu, Chun Cao, Jian LΓΌ arXiv ID 1910.02352 Category cs.LG: Machine Learning Cross-listed cs.SE, stat.ML Citations 30 Venue ESEC/SIGSOFT FSE Last Checked 3 months ago
Abstract
Trained DNN models are increasingly adopted as integral parts of software systems, but they often perform deficiently in the field. A particularly damaging problem is that DNN models often give false predictions with high confidence, due to the unavoidable slight divergences between operation data and training data. To minimize the loss caused by inaccurate confidence, operational calibration, i.e., calibrating the confidence function of a DNN classifier against its operation domain, becomes a necessary debugging step in the engineering of the whole system. Operational calibration is difficult considering the limited budget of labeling operation data and the weak interpretability of DNN models. We propose a Bayesian approach to operational calibration that gradually corrects the confidence given by the model under calibration with a small number of labeled operation data deliberately selected from a larger set of unlabeled operation data. The approach is made effective and efficient by leveraging the locality of the learned representation of the DNN model and modeling the calibration as Gaussian Process Regression. Comprehensive experiments with various practical datasets and DNN models show that it significantly outperformed alternative methods, and in some difficult tasks it eliminated about 71% to 97% high-confidence (>0.9) errors with only about 10\% of the minimal amount of labeled operation data needed for practical learning techniques to barely work.
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€” Machine Learning

Died the same way β€” πŸ‘» Ghosted