arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.03060cs.LG
收藏

基于树的集成学习用于分布外检测

Tree-based Ensemble Learning for Out-of-distribution Detection

University of Georgia(佐治亚大学);U.S. Food and Drug Administration(美国食品药品监督管理局);University of California, Los Angeles(加利福尼亚大学洛杉矶分校)

Zhaiming Shen, Menglun Wang, Guang Cheng, Ming-Jun Lai, Lin Mu, Ruihao Huang, Qi Liu, Hao Zhu

AI总结:

本文提出基于树的分布外检测机制 TOOD,通过树集成模型嵌入的成对汉明距离判断样本分布差异,在表格、图像和文本数据上优于现有方法。

摘要:

在将大多数机器学习模型安全部署到实际应用之前,能否成功判断测试样本是否与训练样本具有相似分布是一个需要首先解决的根本问题。本文提出 TOOD 检测,一种简单而有效的基于树的分布外(TOOD)检测机制,用于判断一组未见样本是否与训练样本具有相似分布。TOOD 检测机制基于计算测试样本树嵌入之间的成对汉明距离,这些树嵌入是通过在分布内训练样本上拟合基于树的集成模型获得的。由于基于树的特性,我们的方法具有可解释性和鲁棒性。此外,我们的方法高效、灵活,适用于各种机器学习任务,并且可以容易地推广到无监督场景。大量实验表明,在各类表格、图像和文本数据上区分分布内与分布外样本时,所提出的方法优于其他最先进的分布外检测方法。

英文摘要:

Being able to successfully determine whether the testing samples has similar distribution as the training samples is a fundamental question to address before we can safely deploy most of the machine learning models into practice. In this paper, we propose TOOD detection, a simple yet effective tree-based out-of-distribution (TOOD) detection mechanism to determine if a set of unseen samples will have similar distribution as of the training samples. The TOOD detection mechanism is based on computing pairwise hamming distance of testing samples' tree embeddings, which are obtained by fitting a tree-based ensemble model through in-distribution training samples. Our approach is interpretable and robust for its tree-based nature. Furthermore, our approach is efficient, flexible to various machine learning tasks, and can be easily generalized to unsupervised setting. Extensive experiments are conducted to show the proposed method outperforms other state-of-the-art out-of-distribution detection methods in distinguishing the in-distribution from out-of-distribution on various tabular, image, and text data.

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。

↑