Mengnan Du

PhD Student

Texas A&M University

Biography

I am currently a 4th year Ph.D. student in Computer Science at the CSE department of Texas A&M University, under supervision of Dr. Xia Hu. I also work closely with Dr. Ben Shneiderman of University of Maryland, and developed a website for Human-Centered AI. Here is my CV.

My research interest is on the broad area of trustworthy machine learning, with a particular interest in the areas of explainable, fair, and robust DNNs. I am particularly interested in the intersection of trustworthy ML and Natural Language Understanding.

Interests

Natural Language Processing
Explainable AI
Fairness in AI

Education

PhD in Computer Science, 2017 - Present
Texas A&M University
MS in Electrical Engineering, 2014 - 2017
Beihang University
BSc in Electrical Engineering, 2010 - 2014
North China Electric Power University

Selected Publications

For full list, please refer to the Google Scholar or CV.

Mengnan Du, Varun Manjunatha, Rajiv Jain, Ruchi Deshpande, Franck Dernoncourt, Jiuxiang Gu, Tong Sun, Xia Hu (2021). Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models. NAACL.

PDF

Huiqi Deng, Na Zou, Mengnan Du, Weifu Chen, Guocan Feng, Xia Hu (2021). A Unified Taylor Framework for Revisiting Attribution Methods. AAAI.

PDF

Ruixiang Tang, Mengnan Du, Yuening Li, Zirui Liu, Xia Hu (2021). Mitigating Gender Bias in Captioning Systems. WWW.

PDF Code

Weijie Fu, Meng Wang, Mengnan Du, Ninghao Liu, Shijie Hao, Xia Hu (2021). Differentiated Explanation of Deep Neural Networks with Skewed Distributions. TPAMI.

PDF Code

Mengnan Du, Ninghao Liu, Xia Hu (2020). Techniques for Interpretable Machine Learning. Communications of the ACM (CACM), Review Article, Highlighted Article on the Cover Page.

Preprint PDF Video

Mengnan Du, Fan Yang, Na Zou, Xia Hu (2020). Fairness in Deep Learning: A Computational Perspective. IEEE Intelligent Systems, Review Article.

PDF Code

Mengnan Du, Shiva Pentyala, Yuening Li, Xia Hu (2020). Towards Generalizable Deepfake Detection with Locality-aware AutoEncoder. CIKM 2020.

PDF Code

Mengnan Du, Ninghao Liu, Fan Yang, Xia Hu (2020). Learning Credible DNNs via Incorporating Prior Knowledge and Model Local Explanation. KAIS.

PDF

Ruixiang Tang, Mengnan Du, Ninghao Liu, Fan Yang, Xia Hu (2020). An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks. KDD.

PDF Code

Haofan Wang, Zifan Wang, Mengnan Du, Fan Yang, Zijian Zhang, Sirui Ding, Piotr Mardziel, Xia Hu (2020). Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks. CVPR 2020 Workshop.

PDF Code

Mengnan Du, Ninghao Liu, Fan Yang, Xia Hu (2019). Learning Credible Deep Neural Networks with Rationale Regularization. ICDM, Best Paper Award Candidate.

PDF

Mengnan Du, Ninghao Liu, Fan Yang, Shuiwang Ji, Xia Hu (2019). On Attribution of Recurrent Neural Network Predictions via Additive Decomposition. WWW 2019, Best Paper Award Candidate.

PDF Code Slides

Fan Yang, Shiva Pentyala, Sina Mohseni, Mengnan Du, Hao Yuan, Rhema Linder, Eric Ragan, Shuiwang Ji, Xia Hu (2019). XFake: Explainable Fake News Detector with Visualizations. WWW 2019 demo track.

PDF

Mengnan Du, Ninghao Liu, Qingquan Song, Xia Hu (2018). Towards Explanation of DNN-based Prediction with Guided Feature Inversion. KDD 2018.

PDF Code Poster

Industry Experience

Adobe, Research Intern.
- Mentor(s): Varun Manjunatha, Tong Sun, Rajiv Jain, Jiuxiang Gu, Ruchi Deshpande, Franck Dernoncourt.
- May 2020 - August 2020
Intel Asia-Pacific Research & Development Ltd, Software Engineer Intern.
- Worked on an AR (Augmented reality) project for Smart glasses.
- March 2017 - August 2017

Awards and Honors

[2020] Graduate Research Excellence Award, Texas A&M University.
[2020] Highlighted Article on the cover page of the Janurary 2020 issue, Communications of the ACM.
[2020] NortonLifeLock Graduate Fellowship 2020 finalist.
[2019] ICDM 2019 Best Paper Candidate.
[2019] WWW 2019 Best Paper Shortlist.
[2019] INFORMS 2019 Best Refereed Paper Finalists.