Hanjing Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hanjing Wang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Qiang Ji
Rensselaer Polytechnic Institute
6 shared publications - Shiqiang Wang
Department of Computer Science, University of Exeter, Exeter, U.K.
2 shared publications - Amit Dhurandhar
IBM Research Yorktown Heights USA
1 shared publication - Bashirul Azam Biswas
Rensselaer Polytechnic Institute
1 shared publication - Dhiraj Joshi
IBM Research Yorktown Heights New York USA
1 shared publication - Hongji Guo
Rensselaer Polytechnic Institute
1 shared publication
Latest Publications
- 3 November 2024
- Published by Springer Nature
- p. 271-288
Integrating Markov Blanket Discovery Into Causal Representation Learning for Domain Generalization
- 3 November 2024
- Published by Springer Nature
- p. 271-288
Integrating Markov Blanket Discovery Into Causal Representation Learning for Domain Generalization
- 29 October 2024
- Published by Springer Nature
- p. 283-301
Bayesian Evidential Deep Learning for Online Action Detection
- 29 October 2024
- Published by Springer Nature
- p. 283-301
Bayesian Evidential Deep Learning for Online Action Detection
- 25 October 2024
- Published by Springer Nature
- p. 237-253
Optimization-Based Uncertainty Attribution Via Learning Informative Perturbations
- 25 October 2024
- Published by Springer Nature
- p. 237-253
Optimization-Based Uncertainty Attribution Via Learning Informative Perturbations
- 24 April 2024
- Published by Springer Nature
- p. 101-112
Semantic Attribution for Explainable Uncertainty Quantification
- 24 April 2024
- Published by Springer Nature
- p. 101-112
Semantic Attribution for Explainable Uncertainty Quantification
- Open Access
Epistemic Uncertainty Quantification For Pre-trained Neural Network
Epistemic uncertainty quantification (UQ) identifies where models lack knowledge. Traditional UQ methods, often based on Bayesian neural networks, are not suitable for pre-trained non-Bayesian models. Our study addresses quantifying epistemic uncertainty for any pre-trained model, which does not need the original training data or model modifications and can ensure broad applicability regardless of network architectures or training techniques. Specifically, we propose a gradient-based approach to assess epistemic uncertainty, analyzing the gradients of outputs relative to model parameters, and thereby indicating necessary model adjustments to accurately represent the inputs. We first explore theoretical guarantees of gradient-based methods for epistemic UQ, questioning the view that this uncertainty is only calculable through differences between multiple models. We further improve gradient-driven UQ by using class-specific weights for integrating gradients and emphasizing distinct contributions from neural network layers. Additionally, we enhance UQ accuracy by combining gradient and perturbation methods to refine the gradients. We evaluate our approach on out-of-distribution detection, uncertainty calibration, and active learning, demonstrating its superiority over current state-of-the-art UQ methods for pre-trained models.
Open AccessEpistemic Uncertainty Quantification For Pre-trained Neural Network
Epistemic uncertainty quantification (UQ) identifies where models lack knowledge. Traditional UQ methods, often based on Bayesian neural networks, are not suitable for pre-trained non-Bayesian models. Our study addresses quantifying epistemic uncertainty for any pre-trained model, which does not need the original training data or model modifications and can ensure broad applicability regardless of network architectures or training techniques. Specifically, we propose a gradient-based approach to assess epistemic uncertainty, analyzing the gradients of outputs relative to model parameters, and thereby indicating necessary model adjustments to accurately represent the inputs. We first explore theoretical guarantees of gradient-based methods for epistemic UQ, questioning the view that this uncertainty is only calculable through differences between multiple models. We further improve gradient-driven UQ by using class-specific weights for integrating gradients and emphasizing distinct contributions from neural network layers. Additionally, we enhance UQ accuracy by combining gradient and perturbation methods to refine the gradients. We evaluate our approach on out-of-distribution detection, uncertainty calibration, and active learning, demonstrating its superiority over current state-of-the-art UQ methods for pre-trained models.
- Open Access
Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning
Predictions made by deep learning models are prone to data perturbations, adversarial attacks, and out-of-distribution inputs. To build a trusted AI system, it is therefore critical to accurately quantify the prediction uncertainties. While current efforts focus on improving uncertainty quantification accuracy and efficiency, there is a need to identify uncertainty sources and take actions to mitigate their effects on predictions. Therefore, we propose to develop explainable and actionable Bayesian deep learning methods to not only perform accurate uncertainty quantification but also explain the uncertainties, identify their sources, and propose strategies to mitigate the uncertainty impacts. Specifically, we introduce a gradient-based uncertainty attribution method to identify the most problematic regions of the input that contribute to the prediction uncertainty. Compared to existing methods, the proposed UA-Backprop has competitive accuracy, relaxed assumptions, and high efficiency. Moreover, we propose an uncertainty mitigation strategy that leverages the attribution results as attention to further improve the model performance. Both qualitative and quantitative evaluations are conducted to demonstrate the effectiveness of our proposed methods.
Open AccessGradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning
Predictions made by deep learning models are prone to data perturbations, adversarial attacks, and out-of-distribution inputs. To build a trusted AI system, it is therefore critical to accurately quantify the prediction uncertainties. While current efforts focus on improving uncertainty quantification accuracy and efficiency, there is a need to identify uncertainty sources and take actions to mitigate their effects on predictions. Therefore, we propose to develop explainable and actionable Bayesian deep learning methods to not only perform accurate uncertainty quantification but also explain the uncertainties, identify their sources, and propose strategies to mitigate the uncertainty impacts. Specifically, we introduce a gradient-based uncertainty attribution method to identify the most problematic regions of the input that contribute to the prediction uncertainty. Compared to existing methods, the proposed UA-Backprop has competitive accuracy, relaxed assumptions, and high efficiency. Moreover, we propose an uncertainty mitigation strategy that leverages the attribution results as attention to further improve the model performance. Both qualitative and quantitative evaluations are conducted to demonstrate the effectiveness of our proposed methods.