Picture for Yongyi Mao

Yongyi Mao

Adversarial Defenses via Vector Quantization

May 23, 2023
Zhiyi Dong, Yongyi Mao

Access Paper or Ask Questions

AdversarialWord Dilution as Text Data Augmentation in Low-Resource Regime

May 16, 2023
Junfan Chen, Richong Zhang, Zheyan Luo, Chunming Hu, Yongyi Mao

* Preprint, Accepted by AAAI 2023

Access Paper or Ask Questions

ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification

May 16, 2023
Junfan Chen, Richong Zhang, Yongyi Mao, Jie Xu

* Accepted at AAAI 2022

Access Paper or Ask Questions

Over-training with Mixup May Hurt Generalization

Mar 02, 2023
Zixuan Liu, Ziqiao Wang, Hongyu Guo, Yongyi Mao

Figure 1 for Over-training with Mixup May Hurt Generalization

Figure 2 for Over-training with Mixup May Hurt Generalization

Figure 3 for Over-training with Mixup May Hurt Generalization

Figure 4 for Over-training with Mixup May Hurt Generalization

* Accepted to ICLR 2023

Access Paper or Ask Questions

Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction

Feb 28, 2023
Kai Sun, Richong Zhang, Samuel Mensah, Nikolaos Aletras, Yongyi Mao, Xudong Liu

Figure 1 for Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction

Figure 2 for Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction

Figure 3 for Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction

Figure 4 for Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction

* Accepted at TheWebConf 2023

Access Paper or Ask Questions

Tighter Information-Theoretic Generalization Bounds from Supersamples

Feb 05, 2023
Ziqiao Wang, Yongyi Mao

Figure 1 for Tighter Information-Theoretic Generalization Bounds from Supersamples

Figure 2 for Tighter Information-Theoretic Generalization Bounds from Supersamples

Figure 3 for Tighter Information-Theoretic Generalization Bounds from Supersamples

Figure 4 for Tighter Information-Theoretic Generalization Bounds from Supersamples

Access Paper or Ask Questions

Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States

Nov 19, 2022
Ziqiao Wang, Yongyi Mao

Figure 1 for Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States

Access Paper or Ask Questions

Information-Theoretic Analysis of Unsupervised Domain Adaptation

Oct 03, 2022
Ziqiao Wang, Yongyi Mao

Figure 1 for Information-Theoretic Analysis of Unsupervised Domain Adaptation

Figure 2 for Information-Theoretic Analysis of Unsupervised Domain Adaptation

Figure 3 for Information-Theoretic Analysis of Unsupervised Domain Adaptation

Figure 4 for Information-Theoretic Analysis of Unsupervised Domain Adaptation

Access Paper or Ask Questions

Cross Domain Few-Shot Learning via Meta Adversarial Training

Mar 01, 2022
Jirui Qi, Richong Zhang, Chune Li, Yongyi Mao

Figure 1 for Cross Domain Few-Shot Learning via Meta Adversarial Training

Figure 2 for Cross Domain Few-Shot Learning via Meta Adversarial Training

Figure 3 for Cross Domain Few-Shot Learning via Meta Adversarial Training

* 6 pages including references, submitted to ACL2021

Access Paper or Ask Questions