1 citations · 2 across the 4 of their papers we have counts for
5 papers
Data Poisoning in Deep Learning: A Survey
Pinlong Zhao, Weiyao Zhu, Pengfei Jiao +2
Deep learning has become a cornerstone of modern artificial intelligence, enabling transformative applications across a wide range of domains. As the core element of deep learning,…
Is Data Valuation Learnable and Interpretable?
Ou Wu, Weiyao Zhu, Mengyang Li
Measuring the value of individual samples is critical for many data-driven tasks, e.g., the training of a deep learning model. Recent literature witnesses the substantial efforts i…
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…
Exploring the Learning Difficulty of Data Theory and Measure
Weiyao Zhu, Ou Wu, Fengguang Su +1
As learning difficulty is crucial for machine learning (e.g., difficulty-based weighting learning strategies), previous literature has proposed a number of learning difficulty meas…
A Mathematical Foundation for Robust Machine Learning based on Bias-Variance Trade-off
Ou Wu, Weiyao Zhu, Yingjun Deng +2
A common assumption in machine learning is that samples are independently and identically distributed (i.i.d). However, the contributions of different samples are not identical in…