Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration
Keywords:Calibration & Uncertainty Quantification
AbstractTo facilitate a wide-spread acceptance of AI systems guiding decision making in real-world applications, trustworthiness of deployed models is key. That is, it is crucial for predictive models to be uncertainty-aware and yield well-calibrated (and thus trustworthy) predictions for both in-domain samples as well as under domain shift. Recent efforts to account for predictive uncertainty include post-processing steps for trained neural networks, Bayesian neural networks as well as alternative non-Bayesian approaches such as ensemble approaches and evidential deep learning. Here, we propose an efficient yet general modelling approach for obtaining well-calibrated, trustworthy probabilities for samples obtained after a domain shift. We introduce a new training strategy combining an entropy-encouraging loss term with an adversarial calibration loss term and demonstrate that this results in well-calibrated and technically trustworthy predictions for a wide range of domain drifts. We comprehensively evaluate previously proposed approaches on different data modalities, a large range of data sets including sequence data, network architectures and perturbation strategies. We observe that our modelling approach substantially outperforms existing state-of-the-art approaches, yielding well-calibrated predictions under domain drift.
How to Cite
Tomani, C., & Buettner, F. (2021). Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration. Proceedings of the AAAI Conference on Artificial Intelligence, 35(11), 9886-9896. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17188
AAAI Technical Track on Machine Learning IV