arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.10697cs.AIcs.LG
收藏

知识图谱中的自动偏差检测

Towards Automatic Bias Detection in Knowledge Graphs

ETH Zürich(苏黎世联邦理工学院);Stanford University(斯坦福大学)

Daphna Keidar, Mian Zhong, Ce Zhang, Yash Raj Shrestha, Bibek Paudel

摘要:

随着最近依赖于知识图谱的社会应用的激增,对确保基于KG的方法中的公平性的技术的需求变得越来越明显。以往的研究表明,幼儿园容易产生各种社会偏见,并提出了多种方法来消除偏见。然而,在这样的研究中,重点一直是去偏置技术,而要去偏置的关系是由用户手动指定的。由于人工规范本身容易受到人类认知偏见的影响,因此需要一种能够量化和暴露偏见的系统,该系统可以支持关于消除偏见的更明智的决定。为了解决文献中的这一差距,我们描述了一个框架,用于识别存在于知识图谱嵌入的偏见,基于数值偏差度量。我们用三种不同的职业预测偏差度量来说明该框架,并且它可以灵活地扩展到进一步的偏差定义和应用。标记为有偏见的关系然后可以交给决策者,以便在随后的去偏见时进行判断。

英文摘要:

With the recent surge in social applications relying on knowledge graphs, the need for techniques to ensure fairness in KG based methods is becoming increasingly evident. Previous works have demonstrated that KGs are prone to various social biases, and have proposed multiple methods for debiasing them. However, in such studies, the focus has been on debiasing techniques, while the relations to be debiased are specified manually by the user. As manual specification is itself susceptible to human cognitive bias, there is a need for a system capable of quantifying and exposing biases, that can support more informed decisions on what to debias. To address this gap in the literature, we describe a framework for identifying biases present in knowledge graph embeddings, based on numerical bias metrics. We illustrate the framework with three different bias measures on the task of profession prediction, and it can be flexibly extended to further bias definitions and applications. The relations flagged as biased can then be handed to decision makers for judgement upon subsequent debiasing.

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。

↑