2 citations · 2 across the 5 of their papers we have counts for
5 papers
Data Valuation by Fusing Global and Local Statistical Information
Xiaoling Zhou, Ou Wu, Michael K. Ng +1
Data valuation has garnered increasing attention in recent years, given the critical role of high-quality data in various applications. Among diverse data valuation approaches, Sha…
Combining Adversaries with Anti-adversaries in Training
Xiaoling Zhou, Nan Yang, Ou Wu
Adversarial training is an effective learning technique to improve the robustness of deep neural networks. In this study, the influence of adversarial training on deep learning mod…
Implicit Counterfactual Data Augmentation for Robust Learning
Xiaoling Zhou, Ou Wu, Michael K. Ng
Machine learning models are prone to capturing the spurious correlations between non-causal attributes and classes, with counterfactual data augmentation being a promising directio…
Understanding Difficulty-based Sample Weighting with a Universal Difficulty Measure
Xiaoling Zhou, Ou Wu, Weiyao Zhu +1
Sample weighting is widely used in deep learning. A large number of weighting methods essentially utilize the learning difficulty of training samples to calculate their weights. In…
Which Samples Should be Learned First: Easy or Hard?
Xiaoling Zhou, Ou Wu
An effective weighting scheme for training samples is essential for learning tasks. Numerous weighting schemes have been proposed. Some schemes take the easy-first mode, whereas so…