arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08769cs.AI
收藏

异构信息网络的公平表示学习

Fair Representation Learning for Heterogeneous Information Networks

University of Maryland, Baltimore County(马里兰大学巴尔的摩县分校);The Hong Kong University of Science and Technology(香港科技大学)

Ziqian Zeng, Rashidul Islam, Kamrun Naher Keya, James Foulds, Yangqiu Song, Shimei Pan

摘要:

最近,人们对人工智能的社会影响给予了很大的关注,特别是对其公平性的关注。越来越多的研究发现了不公平的人工智能系统,并提出了消除偏见的方法,但仍存在许多挑战。异构信息网络(HIN)的表示学习是复杂网络挖掘中使用的基本构建块,具有社会影响力的应用,例如自动职业咨询,但很少有人尝试确保它不会编码或放大有害的偏见,例如就业市场中的性别歧视。为了解决这一差距,在本文中,我们提出了一套全面的去偏置方法公平HIN表示学习,包括基于采样,基于投影,和基于图神经网络(GNNs)的技术。我们系统地研究了这些算法的行为,特别是它们在平衡公平性和预测精度之间的权衡方面的能力。我们评估所提出的方法在自动职业咨询应用程序中的性能,我们减轻职业推荐中的性别偏见。基于对两个数据集的评估结果,我们确定了不同条件下最有效的公平HIN表示学习技术。

英文摘要:

Recently, much attention has been paid to the societal impact of AI, especially concerns regarding its fairness. A growing body of research has identified unfair AI systems and proposed methods to debias them, yet many challenges remain. Representation learning for Heterogeneous Information Networks (HINs), a fundamental building block used in complex network mining, has socially consequential applications such as automated career counseling, but there have been few attempts to ensure that it will not encode or amplify harmful biases, e.g. sexism in the job market. To address this gap, in this paper we propose a comprehensive set of de-biasing methods for fair HINs representation learning, including sampling-based, projection-based, and graph neural networks (GNNs)-based techniques. We systematically study the behavior of these algorithms, especially their capability in balancing the trade-off between fairness and prediction accuracy. We evaluate the performance of the proposed methods in an automated career counseling application where we mitigate gender bias in career recommendation. Based on the evaluation results on two datasets, we identify the most effective fair HINs representation learning techniques under different conditions.

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。

↑