b'Mengnan Du'

Fairness via Representation Neutralization

Existing bias mitigation methods for DNN models primarily work on learni...
06/23/2021 ∙ by Mengnan Du, et al. ∙ 5 ∙ share

read it
A General Taylor Framework for Unifying and Revisiting Attribution Methods

Attribution methods provide an insight into the decision-making process ...
05/28/2021 ∙ by Huiqi Deng, et al. ∙ 0 ∙ share

read it
Learning Disentangled Representations for Time Series

Time-series representation learning is a fundamental task for time-serie...
05/17/2021 ∙ by Yuening Li, et al. ∙ 17 ∙ share

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

Back propagation based visualizations have been proposed to interpret de...
04/14/2021 ∙ by Huiqi Deng, et al. ∙ 0 ∙ share

read it
Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models

Recent studies indicate that NLU models are prone to rely on shortcut fe...
03/11/2021 ∙ by Mengnan Du, et al. ∙ 0 ∙ share

read it
Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation

With the wide use of deep neural networks (DNN), model interpretability ...
01/18/2021 ∙ by Fan Yang, et al. ∙ 0 ∙ share

read it
Deep Serial Number: Computational Watermarking for DNN Intellectual Property Protection

In this paper, we introduce DSN (Deep Serial Number), a new watermarking...
11/17/2020 ∙ by Ruixiang Tang, et al. ∙ 4 ∙ share

read it
A Unified Taylor Framework for Revisiting Attribution Methods

Attribution methods have been developed to understand the decision makin...
08/21/2020 ∙ by Huiqi Deng, et al. ∙ 0 ∙ share

read it
Machine Learning Explanations to Prevent Overtrust in Fake News Detection

Combating fake news and misinformation propagation is a challenging task...
07/24/2020 ∙ by Sina Mohseni, et al. ∙ 16 ∙ share

read it
Mitigating Gender Bias in Captioning Systems

Image captioning has made substantial progress with huge supporting imag...
06/15/2020 ∙ by Ruixiang Tang, et al. ∙ 0 ∙ share

read it
An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks

With the widespread use of deep neural networks (DNNs) in high-stake app...
06/15/2020 ∙ by Ruixiang Tang, et al. ∙ 0 ∙ share

read it
Adversarial Machine Learning: An Interpretation Perspective

Recent years have witnessed the significant advances of machine learning...
04/23/2020 ∙ by Ninghao Liu, et al. ∙ 0 ∙ share

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

Recently, more and more attention has been drawn into the internal mecha...
10/03/2019 ∙ by Haofan Wang, et al. ∙ 25 ∙ share

read it
Sub-Architecture Ensemble Pruning in Neural Architecture Search

Neural architecture search (NAS) is gaining more and more attention in r...
10/01/2019 ∙ by Yijun Bian, et al. ∙ 0 ∙ share

read it
Towards Generalizable Forgery Detection with Locality-aware AutoEncoder

With advancements of deep learning techniques, it is now possible to gen...
09/13/2019 ∙ by Mengnan Du, et al. ∙ 0 ∙ share

read it
Fairness in Deep Learning: A Computational Perspective

Deep learning is increasingly being used in high-stake decision making a...
08/23/2019 ∙ by Mengnan Du, et al. ∙ 0 ∙ share

read it
Learning Credible Deep Neural Networks with Rationale Regularization

Recent explainability related studies have shown that state-of-the-art D...
08/13/2019 ∙ by Mengnan Du, et al. ∙ 0 ∙ share

read it
SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networks

Anomaly detection aims to distinguish observations that are rare and dif...
08/11/2019 ∙ by Yuening Li, et al. ∙ 0 ∙ share

read it
Deep Structured Cross-Modal Anomaly Detection

Anomaly detection is a fundamental problem in data mining field with man...
08/11/2019 ∙ by Yuening Li, et al. ∙ 8 ∙ share

read it
Evaluating Explanation Without Ground Truth in Interpretable Machine Learning

Interpretable Machine Learning (IML) has become increasingly important i...
07/16/2019 ∙ by Fan Yang, et al. ∙ 7 ∙ share

read it
XFake: Explainable Fake News Detector with Visualizations

In this demo paper, we present the XFake system, an explainable fake new...
07/08/2019 ∙ by Fan Yang, et al. ∙ 0 ∙ share

read it
On Attribution of Recurrent Neural Network Predictions via Additive Decomposition

RNN models have achieved the state-of-the-art performance in a wide rang...
03/27/2019 ∙ by Mengnan Du, et al. ∙ 0 ∙ share

read it
Techniques for Interpretable Machine Learning

Interpretable machine learning tackles the important problem that humans...
07/31/2018 ∙ by Mengnan Du, et al. ∙ 0 ∙ share

read it
Towards Explanation of DNN-based Prediction with Guided Feature Inversion

While deep neural networks (DNN) have become an effective computational ...
03/19/2018 ∙ by Mengnan Du, et al. ∙ 0 ∙ share

read it

Mengnan Du

Featured Co-authors

Fan Yang

YI LIU

Xia Hu

Franck Dernoncourt

Shuiwang Ji

Xiao Huang

Subhabrata Mukherjee

Huanhuan Chen

Ahmed Hassan Awadallah

Haifeng Chen

Zijian Zhang

Fairness via Representation Neutralization

A General Taylor Framework for Unifying and Revisiting Attribution Methods

Learning Disentangled Representations for Time Series

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

Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models

Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation

Deep Serial Number: Computational Watermarking for DNN Intellectual Property Protection

A Unified Taylor Framework for Revisiting Attribution Methods

Machine Learning Explanations to Prevent Overtrust in Fake News Detection

Mitigating Gender Bias in Captioning Systems

An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks

Adversarial Machine Learning: An Interpretation Perspective

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

Sub-Architecture Ensemble Pruning in Neural Architecture Search

Towards Generalizable Forgery Detection with Locality-aware AutoEncoder

Fairness in Deep Learning: A Computational Perspective

Learning Credible Deep Neural Networks with Rationale Regularization

SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networks

Deep Structured Cross-Modal Anomaly Detection

Evaluating Explanation Without Ground Truth in Interpretable Machine Learning

XFake: Explainable Fake News Detector with Visualizations

On Attribution of Recurrent Neural Network Predictions via Additive Decomposition

Techniques for Interpretable Machine Learning

Towards Explanation of DNN-based Prediction with Guided Feature Inversion