Label noise is a common issue in real-world datasets that inevitably impacts
the generalization of models. This study focuses on robust classification tasks
where the label noise is instance-dependent. Estimating the transition matrix
accurately in this task is challenging, and methods based on sample selection
often exhibit confirmation bias to varying degrees. Sparse over-parameterized
training (SOP) has been theoretically effective in estimating and recovering
label noise, offering a novel solution for noise-label learning. However, this
study empirically observes and verifies a technical flaw of SOP: the lack of
coordination between model predictions and noise recovery leads to increased
generalization error. To address this, we propose a method called Coordinated
Sparse Recovery (CSR). CSR introduces a collaboration matrix and confidence
weights to coordinate model predictions and noise recovery, reducing error
leakage. Based on CSR, this study designs a joint sample selection strategy and
constructs a comprehensive and powerful learning framework called CSR+. CSR+
significantly reduces confirmation bias, especially for datasets with more
classes and a high proportion of instance-specific noise. Experimental results
on simulated and real-world noisy datasets demonstrate that both CSR and CSR+
achieve outstanding performance compared to methods at the same level.

通过引入协同稀疏恢复（CSR）方法，该研究通过协调模型预测与噪声恢复来减小错误泄露，从而提高模型泛化性能和降低验证偏差。CSR + 是一种基于 CSR 的联合样本选择策略的学习框架，在具有更多类别和高比例实例特定噪声的数据集上表现出显著优势。实验结果证明，CSR 和 CSR + 相比同级别方法，在模拟和真实噪声数据集上都取得了卓越的性能。