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 2201.03668cs.LGcs.AIcs.CVstat.ML
收藏

部分群标号存在时的群鲁棒性

Towards Group Robustness in the presence of Partial Group Labels

University of Wisconsin-Madison(威斯康星大学麦迪逊分校);Cornell University(康奈尔大学);Google Cloud AI Research(谷歌云人工智能研究院)

Vishnu Suresh Lokhande, Kihyuk Sohn, Jinsung Yoon, Madeleine Udell, Chen-Yu Lee, Tomas Pfister

摘要:

当训练由数据集中的伪相关性驱动的机器学习模型时,学习不变表示是一个重要的要求。输入样本和目标标签之间的这些虚假相关性错误地引导神经网络预测,导致某些群体,特别是少数群体的性能较差。针对这些虚假相关性的鲁棒训练需要了解每个样本的组成员关系。在少数或稀有群体的数据标记工作非常费力或组成数据集的个人选择隐藏敏感信息的情况下,这种要求是不切实际的。另一方面,这种数据汇集工作的存在导致包含部分标记的组信息的数据集。最近的工作已经解决了完全无监督的情况下,没有标签的群体。因此,我们的目标是通过解决一个更现实的设置,可以利用部分可用的敏感或群体信息在训练过程中,以填补文献中缺失的差距。首先,我们构造一个约束集,并推导出一个高概率界的组分配属于该集合。其次,我们提出了一个算法,优化最坏的组分配的约束集。通过对图像和表格数据集的实验,我们显示了少数群体性能的改善,同时保持了各组的整体聚合准确性。

英文摘要:

Learning invariant representations is an important requirement when training machine learning models that are driven by spurious correlations in the datasets. These spurious correlations, between input samples and the target labels, wrongly direct the neural network predictions resulting in poor performance on certain groups, especially the minority groups. Robust training against these spurious correlations requires the knowledge of group membership for every sample. Such a requirement is impractical in situations where the data labeling efforts for minority or rare groups are significantly laborious or where the individuals comprising the dataset choose to conceal sensitive information. On the other hand, the presence of such data collection efforts results in datasets that contain partially labeled group information. Recent works have tackled the fully unsupervised scenario where no labels for groups are available. Thus, we aim to fill the missing gap in the literature by tackling a more realistic setting that can leverage partially available sensitive or group information during training. First, we construct a constraint set and derive a high probability bound for the group assignment to belong to the set. Second, we propose an algorithm that optimizes for the worst-off group assignments from the constraint set. Through experiments on image and tabular datasets, we show improvements in the minority group's performance while preserving overall aggregate accuracy across groups.

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。

↑