Picture for Xinyang Zhang

Xinyang Zhang

Patton: Language Model Pretraining on Text-Rich Networks

May 20, 2023
Bowen Jin, Wentao Zhang, Yu Zhang, Yu Meng, Xinyang Zhang, Qi Zhu, Jiawei Han

Figure 1 for Patton: Language Model Pretraining on Text-Rich Networks

Figure 2 for Patton: Language Model Pretraining on Text-Rich Networks

Figure 3 for Patton: Language Model Pretraining on Text-Rich Networks

Figure 4 for Patton: Language Model Pretraining on Text-Rich Networks

* ACL 2023. (Code: https://github.com/PeterGriffinJin/Patton)

Access Paper or Ask Questions

i-Algebra: Towards Interactive Interpretability of Deep Neural Networks

Jan 22, 2021
Xinyang Zhang, Ren Pang, Shouling Ji, Fenglong Ma, Ting Wang

Figure 1 for i-Algebra: Towards Interactive Interpretability of Deep Neural Networks

Figure 2 for i-Algebra: Towards Interactive Interpretability of Deep Neural Networks

Figure 3 for i-Algebra: Towards Interactive Interpretability of Deep Neural Networks

Figure 4 for i-Algebra: Towards Interactive Interpretability of Deep Neural Networks

* Accepted by the 35th AAAI Conference on Artificial Intelligence (AAAI '21)

Access Paper or Ask Questions

Trojaning Language Models for Fun and Profit

Aug 01, 2020
Xinyang Zhang, Zheng Zhang, Ting Wang

Figure 1 for Trojaning Language Models for Fun and Profit

Figure 2 for Trojaning Language Models for Fun and Profit

Figure 3 for Trojaning Language Models for Fun and Profit

Figure 4 for Trojaning Language Models for Fun and Profit

* 19 pages (14 for main text, 5 for appendix), 6 figures, under review

Access Paper or Ask Questions

AdvMind: Inferring Adversary Intent of Black-Box Attacks

Jun 16, 2020
Ren Pang, Xinyang Zhang, Shouling Ji, Xiapu Luo, Ting Wang

Figure 1 for AdvMind: Inferring Adversary Intent of Black-Box Attacks

Figure 2 for AdvMind: Inferring Adversary Intent of Black-Box Attacks

Figure 3 for AdvMind: Inferring Adversary Intent of Black-Box Attacks

Figure 4 for AdvMind: Inferring Adversary Intent of Black-Box Attacks

* Accepted as a full paper at KDD 2020

Access Paper or Ask Questions