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 2502.15992cs.LG
收藏

人类引导的透明回归模型学习

Human Guided Learning of Transparent Regression Models

Johannes Gutenberg-Universität Mainz(美因茨约翰内斯古腾堡大学);Institut für Informatik(计算机科学学院)

Lukas Pensel, Stefan Kramer

AI总结:

针对排列回归新任务,提出人在回路的HuGuR方法,将人类可理解的顺序约束作为特征融入梯度提升回归模型,支持交互式调整,小数据集表现优于基线且模型透明可解释。

摘要:

我们提出了一种人在回路(HIL)的排列回归方法,排列回归是为给定的物品排序预测连续值的新任务。该模型是梯度提升回归模型,将x < y形式的简单人类可理解约束(即物品x必须在物品y之前)作为二值特征纳入其中。该方法名为HuGuR(人类引导回归),可让人类探索此类透明回归模型的搜索空间。用户与HuGuR交互时,可交互式添加、移除和优化顺序约束,同时系数会被实时计算。我们通过一项用户研究评估HuGuR,并在9个数据集上将用户构建的模型与多个基线的性能进行比较。结果表明,用户构建的模型在小数据集上优于对比方法,总体性能与其他方法相当,且原则上人类可以理解。在来自同一领域的更大数据集上,机器生成的模型开始优于用户构建的模型。未来工作将研究用户对自行构建的模型的信任度,以及该方案如何迁移到其他模式领域,如字符串、序列、树或图。

英文摘要:

We present a human-in-the-loop (HIL) approach to permutation regression, the novel task of predicting a continuous value for a given ordering of items. The model is a gradient boosted regression model that incorporates simple human-understandable constraints of the form x < y, i.e. item x has to be before item y, as binary features. The approach, HuGuR (Human Guided Regression), lets a human explore the search space of such transparent regression models. Interacting with HuGuR, users can add, remove, and refine order constraints interactively, while the coefficients are calculated on the fly. We evaluate HuGuR in a user study and compare the performance of user-built models with multiple baselines on 9 data sets. The results show that the user-built models outperform the compared methods on small data sets and in general perform on par with the other methods, while being in principle understandable for humans. On larger datasets from the same domain, machine-induced models begin to outperform the user-built models. Further work will study the trust users have in models when constructed by themselves and how the scheme can be transferred to other pattern domains, such as strings, sequences, trees, or graphs.

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。

↑