arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.08309cs.LGcs.AI
收藏

AdaCC:不平衡分类的累积成本敏感提升

AdaCC: Cumulative Cost-Sensitive Boosting for Imbalanced Classification

Leibniz University of Hannover(汉诺威莱布尼茨大学);Centre of Research and Technology Hellas(希腊研究与技术中心);Free University of Berlin(柏林自由大学)

Vasileios Iosifidis, Symeon Papadopoulos, Bodo Rosenhahn, Eirini Ntoutsi

摘要:

类不平衡对机器学习提出了一个重大挑战,因为大多数监督学习模型可能会对多数类表现出偏见,而在少数类中表现不佳。成本敏感学习通过不同地对待类来解决这个问题,通常通过用户定义的固定误分类成本矩阵作为输入提供给学习者来制定。这样的参数调整是一个具有挑战性的任务,需要领域知识,而且,错误的调整可能会导致整体预测性能恶化。在这项工作中,我们提出了一种新的成本敏感的不平衡数据的提升方法,动态调整错误分类成本的提升轮响应模型的性能,而不是使用一个固定的错误分类成本矩阵。我们的方法称为AdaCC,是无参数的,因为它依赖于boosting模型的累积行为,以便调整下一轮boosting的误分类成本,并且具有关于训练误差的理论保证。对来自不同领域的27个具有高类别不平衡的真实世界数据集的实验表明,我们的方法优于12种最先进的成本敏感的提升方法,这些方法在不同的测量中表现出一致的改进,例如,AUC在[0.3%-28.56%]的范围内,平衡精度在[3.4%-21.4%]的范围内,gmean为4.8%~ 45%,回忆率为7.4%~ 85.5%。

英文摘要:

Class imbalance poses a major challenge for machine learning as most supervised learning models might exhibit bias towards the majority class and under-perform in the minority class. Cost-sensitive learning tackles this problem by treating the classes differently, formulated typically via a user-defined fixed misclassification cost matrix provided as input to the learner. Such parameter tuning is a challenging task that requires domain knowledge and moreover, wrong adjustments might lead to overall predictive performance deterioration. In this work, we propose a novel cost-sensitive boosting approach for imbalanced data that dynamically adjusts the misclassification costs over the boosting rounds in response to model's performance instead of using a fixed misclassification cost matrix. Our method, called AdaCC, is parameter-free as it relies on the cumulative behavior of the boosting model in order to adjust the misclassification costs for the next boosting round and comes with theoretical guarantees regarding the training error. Experiments on 27 real-world datasets from different domains with high class imbalance demonstrate the superiority of our method over 12 state-of-the-art cost-sensitive boosting approaches exhibiting consistent improvements in different measures, for instance, in the range of [0.3%-28.56%] for AUC, [3.4%-21.4%] for balanced accuracy, [4.8%-45%] for gmean and [7.4%-85.5%] for recall.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑