Search Results - "Du, Mengnan"

Fairness in Deep Learning: A Computational Perspective by Du, Mengnan, Yang, Fan, Zou, Na, Hu, Xia

“…Fairness in deep learning has attracted tremendous attention recently, as deep learning is increasingly being used in high-stake decision making applications…”
Get full text

Learning credible DNNs via incorporating prior knowledge and model local explanation by Du, Mengnan, Liu, Ninghao, Yang, Fan, Hu, Xia

“…Recent studies have shown that state-of-the-art DNNs are not always credible, despite their impressive performance on the hold-out test set of a variety of…”
Get full text

Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks by Wang, Haofan, Wang, Zifan, Du, Mengnan, Yang, Fan, Zhang, Zijian, Ding, Sirui, Mardziel, Piotr, Hu, Xia

“…Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific…”
Get full text

A deep learning approach for identifying cancer survivors living with post-traumatic stress disorder on Twitter by Ismail, Nur Hafieza, Liu, Ninghao, Du, Mengnan, He, Zhe, Hu, Xia

“…Emotions after surviving cancer can be complicated. The survivors may have gained new strength to continue life, but some of them may begin to deal with…”
Get full text

Towards structured NLP interpretation via graph explainers by Yuan, Hao, Yang, Fan, Du, Mengnan, Ji, Shuiwang, Hu, Xia

“…Natural language processing (NLP) models have been increasingly deployed in real‐world applications, and interpretation for textual data has also attracted…”
Get full text

Salient object detection via region contrast and graph regularization by Wu, Xingming, Du, Mengnan, Chen, Weihai, Wang, Jianhua

“…Detection of salient objects in an image is now gaining increasing research interest in computer vision community. In this study, a novel region-contrast based…”
Get full text

Unifying Fourteen Post-Hoc Attribution Methods With Taylor Interactions by Deng, Huiqi, Zou, Na, Du, Mengnan, Chen, Weifu, Feng, Guocan, Yang, Ziwei, Li, Zheyang, Zhang, Quanshi

“…Various attribution methods have been developed to explain deep neural networks (DNNs) by inferring the attribution/importance/contribution score of each input…”
Get full text

Subarchitecture Ensemble Pruning in Neural Architecture Search by Bian, Yijun, Song, Qingquan, Du, Mengnan, Yao, Jun, Chen, Huanhuan, Hu, Xia

“…Neural architecture search (NAS) is gaining more and more attention in recent years because of its flexibility and remarkable capability to reduce the burden…”
Get full text

Mitigating social biases of pre-trained language models via contrastive self-debiasing with double data augmentation by Li, Yingji, Du, Mengnan, Song, Rui, Wang, Xin, Sun, Mingchen, Wang, Ying

“…Pre-trained Language Models (PLMs) have been shown to inherit and even amplify the social biases contained in the training corpus, leading to undesired…”
Get full text

Differentiated Explanation of Deep Neural Networks With Skewed Distributions by Fu, Weijie, Wang, Meng, Du, Mengnan, Liu, Ninghao, Hao, Shijie, Hu, Xia

“…Over the last decade, deep neural networks (DNNs) are regarded as black-box methods, and their decisions are criticized for the lack of explainability…”
Get full text

When Search Engine Services meet Large Language Models: Visions and Challenges by Xiong, Haoyi, Bian, Jiang, Li, Yuchen, Li, Xuhong, Du, Mengnan, Wang, Shuaiqiang, Yin, Dawei, Helal, Sumi

“…Combining Large Language Models (LLMs) with search engine services marks a significant shift in the field of services computing, opening up new possibilities…”
Get full text

Fair Machine Learning in Healthcare: A Survey by Feng, Qizhang, Du, Mengnan, Zou, Na, Hu, Xia

“…The digitization of healthcare data coupled with advances in computational capabilities has propelled the adoption of machine learning (ML) in healthcare…”
Get full text

Deep Neural Networks Explainability: Algorithms and Applications by Du, Mengnan

“…Deep neural networks (DNNs) are progressing at an astounding rate, and these models have a wide range of real-world applications, such as movie recommendations…”
Get full text

Exploiting deep convolutional network and patch-level CRFs for indoor semantic segmentation by Xingming Wu, Mengnan Du, Weihai Chen, Zhengguo Li

“…Recent advances in semantic segmentation have mostly been achieved by utilizing deep convolutional neural networks (CNNs). In this paper, a novel indoor…”
Get full text

Supervised training and contextually guided salient object detection by Du, Mengnan, Wu, Xingming, Chen, Weihai, Li, Zhengguo

“…•Supervised salient object detection method performs better than heuristic methods.•Multi-scale fusion is capable of turning several weak saliency maps into a…”
Get full text

Understanding Social Biases Behind Location Names in Contextual Word Embedding Models by Wu, Fangsheng, Du, Mengnan, Fan, Chao, Tang, Ruixiang, Yang, Yang, Mostafavi, Ali, Hu, Xia

“…Embeddings of textual data containing location names (e.g., social media posts) have essential applications in various contexts such as marketing and disaster…”
Get full text

Fusing region contrast and graph regularization for saliency detection by Mengnan Du, Xingming Wu, Weihai Chen, Jianhua Wang

“…Automatic detection of salient object from a static image is a highly active area of computer vision research. In this paper, we propose an effective…”
Get full text

Comparative Analysis of Demonstration Selection Algorithms for LLM In-Context Learning by Shu, Dong, Du, Mengnan

“…In-context learning can help Large Language Models (LLMs) to adapt new tasks without additional training. However, this performance heavily depends on the…”
Get full text

Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning by Hu, Jingyu, Liu, Weiru, Du, Mengnan

“…Recent studies highlight the effectiveness of using in-context learning (ICL) to steer large language models (LLMs) in processing tabular data, a challenging…”
Get full text

DataFrame QA: A Universal LLM Framework on DataFrame Question Answering Without Data Exposure by Ye, Junyi, Du, Mengnan, Wang, Guiling

“…This paper introduces DataFrame question answering (QA), a novel task that utilizes large language models (LLMs) to generate Pandas queries for information…”
Get full text