Identifiability of Label Noise Transition Matrix
Identifiability of Label Noise Transition Matrix
复制标题
DOI：
--
复制
发表时间：
2022-02
期刊：
影响因子：
--
通讯作者：
Yang Liu
中科院分区：
文献类型：
--
作者：
Yang Liu
噪声转移矩阵在噪声标签学习问题中起着核心作用。除许多其他原因外，大量现有解决方案依赖于对其的访问。在没有真实标签的情况下识别和估计转移矩阵是一项关键且具有挑战性的任务。当标签噪声转换取决于每个实例时，识别依赖于实例的噪声转换矩阵的问题变得更具挑战性。尽管最近的工作提出了从依赖实例的噪声标签中学习的解决方案，但该领域对于何时可以识别此类问题缺乏统一的理解。本文的目标是表征标签噪声转移矩阵的可识别性。基于 Kruskal 的可识别性结果，我们能够证明多个噪声标签在识别实例级别的一般情况的噪声转移矩阵时的必要性。我们进一步实例化结果来解释最先进的解决方案的成功以及额外的假设如何减轻对多个噪声标签的要求。我们的结果还表明，解开的特征有助于上述识别任务，并且我们提供了经验证据。
The noise transition matrix plays a central role in the problem of learning with noisy labels. Among many other reasons, a large number of existing solutions rely on access to it. Identifying and estimating the transition matrix without ground truth labels is a critical and challenging task. When label noise transition depends on each instance, the problem of identifying the instance-dependent noise transition matrix becomes substantially more challenging. Despite recent works proposing solutions for learning from instance-dependent noisy labels, the field lacks a unified understanding of when such a problem remains identifiable. The goal of this paper is to characterize the identifiability of the label noise transition matrix. Building on Kruskal's identifiability results, we are able to show the necessity of multiple noisy labels in identifying the noise transition matrix for the generic case at the instance level. We further instantiate the results to explain the successes of the state-of-the-art solutions and how additional assumptions alleviated the requirement of multiple noisy labels. Our result also reveals that disentangled features are helpful in the above identification task and we provide empirical evidence.