Instance-dependent Label-noise Learning under a Structural Causal Model
This addresses label noise in datasets like SVHN and CIFAR, which can degrade deep learning performance, offering a novel solution with broad applicability.
The paper tackles the problem of label noise in deep learning by proposing a generative approach that leverages a structural causal model to exploit causal information between instances and labels, which empirically outperforms state-of-the-art methods on synthetic and real-world datasets.
Label noise will degenerate 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., SVHN and CIFAR, the distributions of P(X) and P(Y|X) are 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. In this paper, by leveraging a structural causal model, we propose a novel generative approach for instance-dependent label-noise learning. In particular, we show that properly modeling the instances will contribute to the identifiability of the label noise transition matrix and thus lead to a better classifier. Empirically, our method outperforms all state-of-the-art methods on both synthetic and real-world label-noise datasets.