论文标题
弥合差距：统一神经网络二进制分类器的培训和评估
Bridging the Gap: Unifying the Training and Evaluation of Neural Network Binary Classifiers
论文作者
论文摘要
尽管经常对诸如准确性和$ f_1 $ score之类的指标进行评估神经网络二进制分类器，但它们通常接受以跨凝性目标进行培训。如何解决这个训练评估差距？尽管已经采用了特定的技术来优化某些基于混淆矩阵的指标，但在某些情况下，将这些技术推广到其他指标是挑战或不可能的。还提出了对抗性学习方法通过基于混淆矩阵的指标来优化网络，但它们往往比常见的培训方法慢得多。在这项工作中，我们提出了一种统一的方法，用于训练神经网络二进制分类器，该方法将Heaviside函数的可区分近似值与使用软集的典型混淆矩阵值的概率视图结合在一起。我们的理论分析表明，使用我们的方法优化给定的评估度量标准，例如$ f_1 $ -score，具有软组，我们的广泛实验表明了我们在多个域中方法的有效性。
While neural network binary classifiers are often evaluated on metrics such as Accuracy and $F_1$-Score, they are commonly trained with a cross-entropy objective. How can this training-evaluation gap be addressed? While specific techniques have been adopted to optimize certain confusion matrix based metrics, it is challenging or impossible in some cases to generalize the techniques to other metrics. Adversarial learning approaches have also been proposed to optimize networks via confusion matrix based metrics, but they tend to be much slower than common training methods. In this work, we propose a unifying approach to training neural network binary classifiers that combines a differentiable approximation of the Heaviside function with a probabilistic view of the typical confusion matrix values using soft sets. Our theoretical analysis shows the benefit of using our method to optimize for a given evaluation metric, such as $F_1$-Score, with soft sets, and our extensive experiments show the effectiveness of our approach in several domains.
