Trustworthy artificial intelligence: a review
Artificial intelligence (AI) and algorithmic decision making are having a profound impact on
our daily lives. These systems are vastly used in different high-stakes applications like …
our daily lives. These systems are vastly used in different high-stakes applications like …
A survey on bias and fairness in machine learning
With the widespread use of artificial intelligence (AI) systems and applications in our
everyday lives, accounting for fairness has gained significant importance in designing and …
everyday lives, accounting for fairness has gained significant importance in designing and …
Source localization of graph diffusion via variational autoencoders for graph inverse problems
Graph diffusion problems such as the propagation of rumors, computer viruses, or smart grid
failures are ubiquitous and societal. Hence it is usually crucial to identify diffusion sources …
failures are ubiquitous and societal. Hence it is usually crucial to identify diffusion sources …
Fairness metrics and bias mitigation strategies for rating predictions
A Ashokan, C Haas - Information Processing & Management, 2021 - Elsevier
Algorithm fairness is an established line of research in the machine learning domain with
substantial work while the equivalent in the recommender system domain is relatively new …
substantial work while the equivalent in the recommender system domain is relatively new …
Man is to person as woman is to location: Measuring gender bias in named entity recognition
In this paper, we study the bias in named entity recognition (NER) models---specifically, the
difference in the ability to recognize male and female names as PERSON entity types. We …
difference in the ability to recognize male and female names as PERSON entity types. We …
Fairsna: Algorithmic fairness in social network analysis
In recent years, designing fairness-aware methods has received much attention in various
domains, including machine learning, natural language processing, and information …
domains, including machine learning, natural language processing, and information …
Mitigating demographic bias of machine learning models on social media
Y Wang, L Singh - Proceedings of the 3rd ACM Conference on Equity …, 2023 - dl.acm.org
Social media posts have been used to predict different user behaviors and attitudes,
including mental health condition, political affiliation, and vaccine hesitancy. Unfortunately …
including mental health condition, political affiliation, and vaccine hesitancy. Unfortunately …
End-to-end bias mitigation: Removing gender bias in deep learning
T Feldman, A Peake - arXiv preprint arXiv:2104.02532, 2021 - arxiv.org
Machine Learning models have been deployed across many different aspects of society,
often in situations that affect social welfare. Although these models offer streamlined …
often in situations that affect social welfare. Although these models offer streamlined …
Benchmarking bias mitigation algorithms in representation learning through fairness metrics
C Reddy - 2022 - papyrus.bib.umontreal.ca
The rapid use and success of deep learning models in various application domains have
raised significant challenges about the fairness of these models when used in the real world …
raised significant challenges about the fairness of these models when used in the real world …
[PDF][PDF] 公平机器学习: 概念, 分析与设计
古天龙, 李龙, 常亮, 罗义琴 - 计算机学报, 2022 - cjc.ict.ac.cn
1)(暨南大学信息科学技术学院, 广州510632) 2)(桂林电子科技大学广西可信软件重点实验室,
广西桂林541004) 摘要随着人工智能的发展, 机器学习技术越来越多地应用于社会各个领域 …
广西桂林541004) 摘要随着人工智能的发展, 机器学习技术越来越多地应用于社会各个领域 …