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 2408.07772cs.LGstat.ML
收藏

基于人类反馈的分布外学习

Out-of-Distribution Learning with Human Feedback

University of Wisconsin-Madison(威斯康星大学麦迪逊分校);NIWC Pacific(美国海军信息作战司令部太平洋分部)

Haoyue Bai, Xuefeng Du, Katie Rainey, Shibin Parameswaran, Yixuan Li

AI总结:

针对传统分布外学习依赖统计方法与预定义假设、泛化和检测效果受限的问题,提出结合人类反馈的新型框架,通过标注野外少量有价值样本训练分类器与检测器,经理论验证和实验证明性能显著优于现有最优方法。

摘要:

分布外(OOD)学习通常严重依赖统计方法或关于OOD数据分布的预定义假设,这限制了其在实际部署环境中应对OOD泛化和OOD检测等多方面挑战的效果。本文提出了一种结合人类反馈的新型OOD学习框架,该框架能为OOD偏移的本质提供宝贵见解,并指导有效的模型适配。我们的框架利用了野外可免费获取的无标注数据,这些数据捕获了协变量偏移和语义偏移下的环境测试时OOD分布。为利用这类数据,我们的核心思路是选择性地提供人类反馈,从野外数据分布中标注少量有信息价值的样本,随后用这些样本训练一个多分类器和一个OOD检测器。通过借助人类反馈,我们提升了机器学习模型的鲁棒性和可靠性,使其具备更高精度处理OOD场景的能力。我们提供了泛化误差界的理论见解以验证我们的算法。大量实验证明了我们方法的优越性,其性能显著优于当前最先进的方法。

英文摘要:

Out-of-distribution (OOD) learning often relies heavily on statistical approaches or predefined assumptions about OOD data distributions, hindering their efficacy in addressing multifaceted challenges of OOD generalization and OOD detection in real-world deployment environments. This paper presents a novel framework for OOD learning with human feedback, which can provide invaluable insights into the nature of OOD shifts and guide effective model adaptation. Our framework capitalizes on the freely available unlabeled data in the wild that captures the environmental test-time OOD distributions under both covariate and semantic shifts. To harness such data, our key idea is to selectively provide human feedback and label a small number of informative samples from the wild data distribution, which are then used to train a multi-class classifier and an OOD detector. By exploiting human feedback, we enhance the robustness and reliability of machine learning models, equipping them with the capability to handle OOD scenarios with greater precision. We provide theoretical insights on the generalization error bounds to justify our algorithm. Extensive experiments show the superiority of our method, outperforming the current state-of-the-art by a significant margin.

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。

↑