Bridging the Gap: Unifying the Training and Evaluation of Neural Network Binary Classifiers
Bridging the Gap: Unifying the Training and Evaluation of Neural Network Binary Classifiers
复制标题
DOI：
--
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Nathan Tsoi;Kate Candon;Deyuan Li;Yofti Milkessa;M. V'azquez
中科院分区：
文献类型：
--
作者：
Nathan Tsoi;Kate Candon;Deyuan Li;Yofti Milkessa;M. V'azquez
虽然神经网络二元分类器通常根据准确性和$F_1$-Score等指标进行评估，但它们通常使用交叉熵目标进行训练。如何解决培训与评估之间的差距？虽然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具有挑战性的或不可能的。对抗学习方法也被提出通过基于混淆矩阵的度量来优化网络，但它们往往比常见的训练方法慢得多。在这项工作中，我们提出了一种统一的方法来训练神经网络二元分类器，该方法结合了Heaviside函数的可微近似和使用软集的典型混淆矩阵值的概率视图。我们的理论分析表明，使用我们的方法对给定的评估指标（如$F_1$-Score）进行软集优化是有好处的，我们的大量实验表明，我们的方法在几个领域是有效的。
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.