Instance-dependent Label-noise Learning under a Structural Causal Model

Label noise generally degenerates the performance of deep learning algorithms because deep neural networks easily overfit label errors. Let $X$ and $Y$ denote the instance and clean label, respectively. When $Y$ is a cause of $X$, according to which many datasets have been constructed, e. g. , \textit{SVHN} and \textit{CIFAR}, the distributions of $P(X)$ and $P(Y|X)$ are generally entangled. This means that the unsupervised instances are helpful to learn the classifier and thus reduce the side effect of label noise. However, it remains elusive on how to exploit the causal information to handle the label-noise problem. We propose to model and make use of the causal process in order to correct the label-noise effect. Empirically, the proposed method outperforms all state-of-the-art methods on both synthetic and real-world label-noise datasets.

Authors

• Yu Yao Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu, China University of Chinese Academic Sciences, Beijing, China
• Tongliang Liu Sydney AI Centre, The University of Sydney, Sydney
• Mingming Gong University of Melbourne Mohamed bin Zayed University of Artificial Intelligence
• Bo Han Hong Kong Baptist University
• Gang Niu
• Kun Zhang MBZUAI, Abu Dhabi, UAE, Carnegie Mellon University, Pittsburg, USA

Keywords

No keywords are indexed for this paper.