We conduct theoretical studies on streaming-based active learning for binary classification under unknown adversarial label corruptions. In this setting, every time before the learner observes a sample, the adversary decides whether to corrupt the label or not. First, we show that, in a benign corruption setting (which includes the misspecification setting as a special case), with a slight enlargement on the hypothesis elimination threshold, the classical RobustCAL framework can (surprisingly) achieve nearly the same label complexity guarantee as in the non-corrupted setting. However, this algorithm can fail in the general corruption setting. To resolve this drawback, we propose a new algorithm which is provably correct without any assumptions on the presence of corruptions. Furthermore, this algorithm enjoys the minimax label complexity in the non-corrupted setting (which is achieved by RobustCAL) and only requires $\tilde{\mathcal{O}}(C_{\mathrm{total}})$ additional labels in the corrupted setting to achieve $\mathcal{O}(\varepsilon + \frac{C_{\mathrm{total}}}{n})$, where $\varepsilon$ is the target accuracy, $C_{\mathrm{total}}$ is the total number of corruptions and $n$ is the total number of unlabeled samples.
翻译:我们根据未知的对抗性标签腐败进行基于流学的积极积极学习的理论研究, 在未知的对抗性标签腐败下进行二进制分类。 在这种环境下, 每次学习者观察样本之前, 对手都会决定是否腐蚀标签。 首先, 我们显示, 在良好的腐败环境中( 包括错误区分设置为特殊案例), 假设消除阈值稍有扩大, 传统的 RobustCAL 框架可以( 令人惊讶地) 达到与无干扰设置几乎相同的标签复杂性保证 。 但是, 这个算法可以在总体腐败环境下失败。 为了解决这一缺陷, 我们建议一种新的算法可以在不假定存在腐败的情况下完全正确。 此外, 这个算法在非扭曲的环境下( 由RobustAL 实现 ), 只需要$tilde\ mathcal{( matthrm{ ) { (cmathrm{ glob) $ (tal $) 和 number $===n=lal==lal==xx==xx gn= gn=xn=xxxx==x=xx=x=x====xx==x=====================x================================================================================================================================================================================================================================