Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Mengnan Du

Fairness via Representation Neutralization


Jun 23, 2021
Mengnan Du, Subhabrata Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Hassan Awadallah, Xia Hu


  Access Paper or Ask Questions

A General Taylor Framework for Unifying and Revisiting Attribution Methods


May 28, 2021
Huiqi Deng, Na Zou, Mengnan Du, Weifu Chen, Guocan Feng, Xia Hu


  Access Paper or Ask Questions

Learning Disentangled Representations for Time Series


May 21, 2021
Yuening Li, Zhengzhang Chen, Daochen Zha, Mengnan Du, Denghui Zhang, Haifeng Chen, Xia Hu


  Access Paper or Ask Questions

Interpretable Time-series Representation Learning With Multi-Level Disentanglement


May 17, 2021
Yuening Li, Zhengzhang Chen, Daochen Zha, Mengnan Du, Denghui Zhang, Haifeng Chen, Xia Hu


  Access Paper or Ask Questions

Mutual Information Preserving Back-propagation: Learn to Invert for Faithful Attribution


Apr 14, 2021
Huiqi Deng, Na Zou, Weifu Chen, Guocan Feng, Mengnan Du, Xia Hu


  Access Paper or Ask Questions

Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models


Mar 18, 2021
Mengnan Du, Varun Manjunatha, Rajiv Jain, Ruchi Deshpande, Franck Dernoncourt, Jiuxiang Gu, Tong Sun, Xia Hu

* Accepted by NAACL 2021 

  Access Paper or Ask Questions

Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation


Jan 18, 2021
Fan Yang, Ninghao Liu, Mengnan Du, Xia Hu


  Access Paper or Ask Questions

Deep Serial Number: Computational Watermarking for DNN Intellectual Property Protection


Nov 17, 2020
Ruixiang Tang, Mengnan Du, Xia Hu


  Access Paper or Ask Questions

A Unified Taylor Framework for Revisiting Attribution Methods


Aug 21, 2020
Huiqi Deng, Na Zou, Mengnan Du, Weifu Chen, Guocan Feng, Xia Hu


  Access Paper or Ask Questions

Machine Learning Explanations to Prevent Overtrust in Fake News Detection


Jul 27, 2020
Sina Mohseni, Fan Yang, Shiva Pentyala, Mengnan Du, Yi Liu, Nic Lupfer, Xia Hu, Shuiwang Ji, Eric Ragan


  Access Paper or Ask Questions

An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks


Jun 18, 2020
Ruixiang Tang, Mengnan Du, Ninghao Liu, Fan Yang, Xia Hu


  Access Paper or Ask Questions

Mitigating Gender Bias in Captioning Systems


Jun 15, 2020
Ruixiang Tang, Mengnan Du, Yuening Li, Zirui Liu, Xia Hu


  Access Paper or Ask Questions

Adversarial Machine Learning: An Interpretation Perspective


Apr 23, 2020
Ninghao Liu, Mengnan Du, Xia Hu


  Access Paper or Ask Questions

Score-CAM:Improved Visual Explanations Via Score-Weighted Class Activation Mapping


Oct 03, 2019
Haofan Wang, Mengnan Du, Fan Yang, Zijian Zhang

* arXiv admin note: text overlap with arXiv:1610.02391 by other authors 

  Access Paper or Ask Questions

Sub-Architecture Ensemble Pruning in Neural Architecture Search


Oct 01, 2019
Yijun Bian, Qingquan Song, Mengnan Du, Jun Yao, Huanhuan Chen, Xia Hu

* This work was done when the first author was a visiting research scholar at Texas A&M University 

  Access Paper or Ask Questions

Towards Generalizable Forgery Detection with Locality-aware AutoEncoder


Sep 13, 2019
Mengnan Du, Shiva Pentyala, Yuening Li, Xia Hu

* Mengnan Du and Shiva Pentyala contributed equally to this work 

  Access Paper or Ask Questions

Fairness in Deep Learning: A Computational Perspective


Aug 23, 2019
Mengnan Du, Fan Yang, Na Zou, Xia Hu


  Access Paper or Ask Questions

Evaluating Explanation Without Ground Truth in Interpretable Machine Learning


Aug 15, 2019
Fan Yang, Mengnan Du, Xia Hu


  Access Paper or Ask Questions

Learning Credible Deep Neural Networks with Rationale Regularization


Aug 13, 2019
Mengnan Du, Ninghao Liu, Fan Yang, Xia Hu

* ICDM 2019 

  Access Paper or Ask Questions

SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networks


Aug 11, 2019
Yuening Li, Xiao Huang, Jundong Li, Mengnan Du, Na Zou

* 5 pages, in proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM) 

  Access Paper or Ask Questions

Deep Structured Cross-Modal Anomaly Detection


Aug 11, 2019
Yuening Li, Ninghao Liu, Jundong Li, Mengnan Du, Xia Hu

* 8 pages, in Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN) 

  Access Paper or Ask Questions

XFake: Explainable Fake News Detector with Visualizations


Jul 08, 2019
Fan Yang, Shiva K. Pentyala, Sina Mohseni, Mengnan Du, Hao Yuan, Rhema Linder, Eric D. Ragan, Shuiwang Ji, Xia Hu

* 4 pages, WebConf'2019 Demo 

  Access Paper or Ask Questions

On Attribution of Recurrent Neural Network Predictions via Additive Decomposition


Mar 27, 2019
Mengnan Du, Ninghao Liu, Fan Yang, Shuiwang Ji, Xia Hu

* The 2019 Web Conference (WWW 2019) 

  Access Paper or Ask Questions

Techniques for Interpretable Machine Learning


Jul 31, 2018
Mengnan Du, Ninghao Liu, Xia Hu


  Access Paper or Ask Questions

Towards Explanation of DNN-based Prediction with Guided Feature Inversion


May 26, 2018
Mengnan Du, Ninghao Liu, Qingquan Song, Xia Hu


  Access Paper or Ask Questions