arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.04864cs.LG
收藏

THOR:有序回归的基于保留值的排序损失

THOR: Threshold-Based Ranking Loss for Ordinal Regression

Bar-Ilan University(巴伊兰大学)

Tzeviya Sylvia Fuchs, Joseph Keshet

摘要:

在这项工作中,我们提出了一个基于回归的有序回归算法的监督分类的顺序类别的实例。与之前的方法相比,在这项工作中,类别之间的决策边界是预定义的,并且算法学会根据这些预定义的边界将输入示例投影到其适当的分数上。这是通过增加一个新的基于阈值的成对损失函数,旨在最大限度地减少回归误差,这反过来又最大限度地减少平均绝对误差(MAE)的措施。我们实现了我们提出的架构不可知的方法,使用CNN框架的特征提取。五个真实世界的基准测试结果表明,该算法实现了最好的MAE结果相比,最先进的有序回归算法。

英文摘要:

In this work, we present a regression-based ordinal regression algorithm for supervised classification of instances into ordinal categories. In contrast to previous methods, in this work the decision boundaries between categories are predefined, and the algorithm learns to project the input examples onto their appropriate scores according to these predefined boundaries. This is achieved by adding a novel threshold-based pairwise loss function that aims at minimizing the regression error, which in turn minimizes the Mean Absolute Error (MAE) measure. We implemented our proposed architecture-agnostic method using the CNN-framework for feature extraction. Experimental results on five real-world benchmarks demonstrate that the proposed algorithm achieves the best MAE results compared to state-of-the-art ordinal regression algorithms.

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。

↑