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

Add to Chrome

Add to Firefox

Picture for Dongxiao Zhu

Dongxiao Zhu

Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classification

Yao Qiang , Supriya Tumkur Suresh Kumar , Marco Brocanelli , Dongxiao Zhu

Figure 1 for Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classification

Figure 2 for Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classification

Figure 3 for Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classification

Figure 4 for Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classification

* 8 pages, 4 figures

Access Paper or Ask Questions

Adversarially robust and explainable model compression with on-device personalization for NLP applications

Yao Qiang , Supriya Tumkur Suresh Kumar , Marco Brocanelli , Dongxiao Zhu

Figure 1 for Adversarially robust and explainable model compression with on-device personalization for NLP applications

Figure 2 for Adversarially robust and explainable model compression with on-device personalization for NLP applications

Figure 3 for Adversarially robust and explainable model compression with on-device personalization for NLP applications

Figure 4 for Adversarially robust and explainable model compression with on-device personalization for NLP applications

* Need to improve the paper

Access Paper or Ask Questions

Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints

Xin Li , Xiangrui Li , Deng Pan , Dongxiao Zhu

Figure 1 for Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints

Figure 2 for Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints

Figure 3 for Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints

Figure 4 for Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints

* To appear in the proceedings of Thirty-Five AAAI Conference on Artificial Intelligence (AAAI-21)

Access Paper or Ask Questions

Explainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability

Deng Pan , Xiangrui Li , Xin Li , Dongxiao Zhu

Figure 1 for Explainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability

Figure 2 for Explainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability

Figure 3 for Explainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability

Figure 4 for Explainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability

* IJCAI 2020, pages 2690-2696
* Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI)

Access Paper or Ask Questions

Defending against adversarial attacks on medical imaging AI system, classification or detection?

Xin Li , Deng Pan , Dongxiao Zhu

Figure 1 for Defending against adversarial attacks on medical imaging AI system, classification or detection?

Figure 2 for Defending against adversarial attacks on medical imaging AI system, classification or detection?

Figure 3 for Defending against adversarial attacks on medical imaging AI system, classification or detection?

Figure 4 for Defending against adversarial attacks on medical imaging AI system, classification or detection?

Access Paper or Ask Questions

COVID-MobileXpert: On-Device COVID-19 Screening using Snapshots of Chest X-Ray

Xin Li , Chengyin Li , Dongxiao Zhu

Figure 1 for COVID-MobileXpert: On-Device COVID-19 Screening using Snapshots of Chest X-Ray

Figure 2 for COVID-MobileXpert: On-Device COVID-19 Screening using Snapshots of Chest X-Ray

Figure 3 for COVID-MobileXpert: On-Device COVID-19 Screening using Snapshots of Chest X-Ray

Figure 4 for COVID-MobileXpert: On-Device COVID-19 Screening using Snapshots of Chest X-Ray

* COVID-19, CoVid-19, SARS-CoV-2, on-device machine learning, Chest X-Ray (CXR)

Access Paper or Ask Questions

Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach

Yao Qiang , Xin Li , Dongxiao Zhu

Figure 1 for Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach

Figure 2 for Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach

Figure 3 for Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach

Figure 4 for Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach

* to appear in the proceedings of IJCNN'20

Access Paper or Ask Questions

On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks

Xiangrui Li , Xin Li , Deng Pan , Dongxiao Zhu

Figure 1 for On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks

Figure 2 for On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks

Figure 3 for On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks

Figure 4 for On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks

* AAAI2020. Previously this appeared as arXiv:1906.04026v2, which was submitted as a replacement by accident

Access Paper or Ask Questions

Improve SGD Training via Aligning Mini-batches

Xiangrui Li , Deng Pan , Xin Li , Dongxiao Zhu

Figure 1 for Improve SGD Training via Aligning Mini-batches

Figure 2 for Improve SGD Training via Aligning Mini-batches

Figure 3 for Improve SGD Training via Aligning Mini-batches

Figure 4 for Improve SGD Training via Aligning Mini-batches

Access Paper or Ask Questions

Improve SGD Training via Aligning Min-batches

Xiangrui Li , Deng Pan , Xin Li , Dongxiao Zhu

Figure 1 for Improve SGD Training via Aligning Min-batches

Figure 2 for Improve SGD Training via Aligning Min-batches

Figure 3 for Improve SGD Training via Aligning Min-batches

Figure 4 for Improve SGD Training via Aligning Min-batches

Access Paper or Ask Questions