Saiyu Qi — accepted AI-conference papers

2025

Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation

Qi Guo, Zhen Tian, Minghao Yao, Saiyu Qi, Yong Qi, Bingyi Liu

ICCV 2025poster

Federated Unlearning (FU) should satisfy three key requirements: a guarantee of data erasure, preservation of model utility, and reduction of unlearning time. Recent studies focus on identifying and modifying original model parameters relevant to unlearning data. While they can achieve faster unlear…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2020

Stochastic Batch Augmentation with An Effective Distilled Dynamic Soft Label Regularizer

Qian Li, Qingyuan Hu, Yong Qi, Saiyu Qi, Jie Ma, Jian Zhang

IJCAI 2020poster

Data augmentation have been intensively used in training deep neural network to improve the generalization, whether in original space (e.g., image space) or representation space. Although being successful, the connection between the synthesized data and the original data is largely ignored in traini…

Cited by 0 Source ↗PDF ↗Scholar ↗