Zhang Zhiyuan
Peking University
H-index: 12
Asia-China
Top articles of Zhang Zhiyuan
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense | Advances in Neural Information Processing Systems | Zhiyuan Zhang Deli Chen Hao Zhou Fandong Meng Jie Zhou | 2024/2/13 |
Incorporating Pre-trained Model Prompting in Multimodal Stock Volume Movement Prediction | arXiv preprint arXiv:2309.05608 | Ruibo Chen Zhiyuan Zhang Yi Liu Ruihan Bao Keiko Harimoto | 2023/9/11 |
Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias | arXiv preprint arXiv:2305.04547 | Zhiyuan Zhang Deli Chen Hao Zhou Fandong Meng Jie Zhou | 2023/5/8 |
ASAT: Adaptively scaled adversarial training in time series | Neurocomputing | Zhiyuan Zhang Wei Li Ruihan Bao Keiko Harimoto Yunfang Wu | 2023/2/14 |
Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation | arXiv preprint arXiv:2210.06894 | Zhiyuan Zhang Qi Su Xu Sun | 2022/10/13 |
No Stock is an Island: Learning Internal and Relational Attributes of Stocks with Contrastive Learning | Shicheng Li Wei Li Zhiyuan Zhang Ruihan Bao Keiko Harimoto | 2022/12 | |
Stock Trading Volume Prediction with Dual-Process Meta-Learning | Ruibo Chen Wei Li Zhiyuan Zhang Ruihan Bao Keiko Harimoto | 2022/9/19 | |
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models | arXiv preprint arXiv:2210.09545 | Zhiyuan Zhang Lingjuan Lyu Xingjun Ma Chenguang Wang Xu Sun | 2022/10/18 |
Distributional Correlation–Aware Knowledge Distillation for Stock Trading Volume Prediction | Lei Li Zhiyuan Zhang Ruihan Bao Keiko Harimoto Xu Sun | 2022/9/19 | |
Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks | arXiv preprint arXiv:2210.07907 | Sishuo Chen Wenkai Yang Zhiyuan Zhang Xiaohan Bi Xu Sun | 2022/10/14 |
GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization | arXiv preprint arXiv:2210.06895 | Zhiyuan Zhang Ruixuan Luo Qi Su Xu Sun | 2022/10/13 |
How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data | arXiv preprint arXiv:2109.01300 | Zhiyuan Zhang Lingjuan Lyu Weiqiang Wang Lichao Sun Xu Sun | 2021/9/3 |
Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects | Zhiyuan Zhang Xuancheng Ren Qi Su Xu Sun Bin He | 2021/6 | |
Exploring the vulnerability of deep neural networks: A study of parameter corruption | Proceedings of the AAAI Conference on Artificial Intelligence | Xu Sun Zhiyuan Zhang Xuancheng Ren Ruixuan Luo Liangyou Li | 2021/5/18 |
Be careful about poisoned word embeddings: Exploring the vulnerability of the embedding layers in NLP models | arXiv preprint arXiv:2103.15543 | Wenkai Yang Lei Li Zhiyuan Zhang Xuancheng Ren Xu Sun | 2021/3/29 |
Adversarial parameter defense by multi-step risk minimization | Neural Networks | Zhiyuan Zhang Ruixuan Luo Xuancheng Ren Qi Su Liangyou Li | 2021/12/1 |
Raise a child in large language model: Towards effective and generalizable fine-tuning | arXiv preprint arXiv:2109.05687 | Runxin Xu Fuli Luo Zhiyuan Zhang Chuanqi Tan Baobao Chang | 2021/9/13 |
Rethinking Skip Connection with Layer Normalization | arXiv preprint arXiv:2105.07205 | Fenglin Liu Xuancheng Ren Zhiyuan Zhang Xu Sun Yuexian Zou | 2021/5/15 |
Memorized sparse backpropagation | Neurocomputing | Zhiyuan Zhang Pengcheng Yang Xuancheng Ren Qi Su Xu Sun | 2020/11/20 |
Pretrain-KGE: learning knowledge representation from pretrained language models | Zhiyuan Zhang Xiaoqian Liu Yi Zhang Qi Su Xu Sun | 2020/11 |