activity
20182021
most citedXFake: Explainable Fake News Detector with Visualizations

103 citations · 167 across the 9 of their papers we have counts for

collaborators

21 papers

cs.LG202128 cited

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…

cs.LG20216 cited

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…

cs.LG2021

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…

cs.CL202111 cited

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…

cs.LG20214 cited

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…

stat.ML2020

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…