How optimal transport can tackle gender biases in multi-class neural-network classifiers for job recommendations?
Institut de Mathématiques de Toulouse(图卢兹数学研究所);CNRS(法国国家科学研究中心);Université de Toulouse(图卢兹大学);Institut de Recherche en Informatique de Toulouse(图卢兹计算机科学研究所);AKKODIS group(AKKODIS集团)
Automatic recommendation systems based on deep neural networks have become extremely popular during the last decade. Some of these systems can however be used for applications which are ranked as High Risk by the European Commission in the A.I. act, as for instance for online job candidate recommendation. When used in the European Union, commercial AI systems for this purpose will then be required to have to proper statistical properties with regard to potential discrimination they could engender. This motivated our contribution, where we present a novel optimal transport strategy to mitigate undesirable algorithmic biases in multi-class neural-network classification. Our stratey is model agnostic and can be used on any multi-class classification neural-network model. To anticipate the certification of recommendation systems using textual data, we then used it on the Bios dataset, for which the learning task consists in predicting the occupation of female and male individuals, based on their LinkedIn biography. Results show that it can reduce undesired algorithmic biases in this context to lower levels than a standard strategy.
Don't Judge Me by My Face : An Indirect Adversarial Approach to Remove Sensitive Information From Multimodal Neural Representation in Asynchronous Job Video Interviews
Men Are Elected, Women Are Married: Events Gender Bias on Wikipedia
University of Southern California(南加利福尼亚大学);Information Sciences Institute, University of Southern California(南加利福尼亚大学信息科学研究所);University of California, Los Angeles(加利福尼亚大学洛杉矶分校)
关于信息检索(IR)系统中的社会偏见的足迹的关注已经在以前的几项研究中提出。在这项工作中,我们研究了各种最近的IR模型的角度来看,在其检索结果的性别偏见的程度。为此,我们首先提供了一个偏差测量框架,其中包括两个指标来量化的程度不平衡的存在,性别相关的概念在一个给定的IR模型的排名列表。为了通过框架检查IR模型,我们创建了一个由人类注释者选择的非性别查询数据集。将这些查询应用于MS MARCO Passage检索集合,然后测量BM 25模型和几个最近的神经排名模型的性别偏见。结果表明,虽然所有模型都强烈偏向男性,但神经模型,特别是基于情境嵌入模型的模型,显着加剧了性别偏见。我们的实验还表明,当神经模型利用迁移学习时,即当它们使用(已经有偏见的)预训练嵌入时,神经模型的性别偏见会整体增加。
Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You
TU Darmstadt(图宾根大学);Ontocord(Ontocord公司);Technical University of Munich (TUM)(慕尼黑技术大学);Munich Center for Machine Learning(慕尼黑机器学习中心);CERTAIN(CERTAIN公司);DFKI(德意志联邦防务研究院);Charles University Prague(布拉格查理大学);Centre for Cognitive Science, Darmstadt(达姆施塔特认知科学中心);Munich Data Science Institute(慕尼黑数据科学研究所)
Towards Understanding Gender Bias in Relation Extraction
Department of Computer Science, UC Santa Barbara(加州大学圣塔芭芭拉分校计算机科学系);Department of Computer Science, UC Los Angeles(加州大学洛杉矶分校计算机科学系);School of Interactive Computing, Georgia Institute of Technology(佐治亚理工学院交互计算学院)