103 citations · 167 across the 9 of their papers we have counts for
21 papers
Fairness via Representation Neutralization
Mengnan Du, Subhabrata Mukherjee, Guanchu Wang +3
Existing bias mitigation methods for DNN models primarily work on learning debiased encoders. This process not only requires a lot of instance-level annotations for sensitive attri…
Learning Disentangled Representations for Time Series
Yuening Li, Zhengzhang Chen, Daochen Zha +4
Time-series representation learning is a fundamental task for time-series analysis. While significant progress has been made to achieve accurate representations for downstream appl…
Mutual Information Preserving Back-propagation: Learn to Invert for Faithful Attribution
Huiqi Deng, Na Zou, Weifu Chen +3
Back propagation based visualizations have been proposed to interpret deep neural networks (DNNs), some of which produce interpretations with good visual quality. However, there ex…
Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models
Mengnan Du, Varun Manjunatha, Rajiv Jain +5
Recent studies indicate that NLU models are prone to rely on shortcut features for prediction, without achieving true language understanding. As a result, these models fail to gene…
Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation
Fan Yang, Ninghao Liu, Mengnan Du +1
With the wide use of deep neural networks (DNN), model interpretability has become a critical concern, since explainable decisions are preferred in high-stake scenarios. Current in…
A Unified Taylor Framework for Revisiting Attribution Methods
Huiqi Deng, Na Zou, Mengnan Du +3
Attribution methods have been developed to understand the decision-making process of machine learning models, especially deep neural networks, by assigning importance scores to ind…