Zhang Ruiheng, Cao Zhe, Yang Shuo, Si Lingyu, Sun Haoyang, Xu Lixin, Sun Fuchun
IEEE Trans Neural Netw Learn Syst. 2025 Feb;36(2):3730-3743. doi: 10.1109/TNNLS.2023.3347633. Epub 2025 Feb 6.
The label transition matrix has emerged as a widely accepted method for mitigating label noise in machine learning. In recent years, numerous studies have centered on leveraging deep neural networks to estimate the label transition matrix for individual instances within the context of instance-dependent noise. However, these methods suffer from low search efficiency due to the large space of feasible solutions. Behind this drawback, we have explored that the real murderer lies in the invalid class transitions, that is, the actual transition probability between certain classes is zero but is estimated to have a certain value. To mask the invalid class transitions, we introduced a human-cognition-assisted method with structural information from human cognition. Specifically, we introduce a structured transition matrix network (STMN) designed with an adversarial learning process to balance instance features and prior information from human cognition. The proposed method offers two advantages: 1) better estimation effectiveness is obtained by sparing the transition matrix and 2) better estimation accuracy is obtained with the assistance of human cognition. By exploiting these two advantages, our method parametrically estimates a sparse label transition matrix, effectively converting noisy labels into true labels. The efficiency and superiority of our proposed method are substantiated through comprehensive comparisons with state-of-the-art methods on three synthetic datasets and a real-world dataset. Our code will be available at https://github.com/WheatCao/STMN-Pytorch.
标签转移矩阵已成为机器学习中减轻标签噪声的一种广泛接受的方法。近年来，许多研究集中在利用深度神经网络在实例相关噪声的背景下估计单个实例的标签转移矩阵。然而，由于可行解空间较大，这些方法存在搜索效率低的问题。在这个缺点背后，我们探究发现真正的问题在于无效的类别转移，即某些类别之间的实际转移概率为零，但却被估计为有一定的值。为了掩盖无效的类别转移，我们引入了一种具有人类认知结构信息的人类认知辅助方法。具体来说，我们引入了一个通过对抗学习过程设计的结构化转移矩阵网络（STMN），以平衡实例特征和来自人类认知的先验信息。所提出的方法具有两个优点：1）通过保留转移矩阵获得了更好的估计有效性，2）在人类认知的帮助下获得了更好的估计准确性。通过利用这两个优点，我们的方法参数化地估计了一个稀疏的标签转移矩阵，有效地将噪声标签转换为真实标签。通过在三个合成数据集和一个真实世界数据集上与现有方法进行全面比较，证实了我们所提出方法的效率和优越性。我们的代码将在https://github.com/WheatCao/STMN-Pytorch上提供。
