Proving unfairness of decision making systems without model access

Article Computer Science, Artificial Intelligence

How fair can we go in machine learning? Assessing the boundaries of accuracy and fairness

Ana Valdivia et al.

Summary: This study introduces a novel methodology to explore the tradeoff between accuracy and fairness in machine learning models. By optimizing multiple measures, classifiers can be made fairer with a small cost on classification accuracy. The focus is on logistic regression and decision tree classifiers.

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

A Comprehensive Survey on Transfer Learning

Fuzhen Zhuang et al.

Summary: Transfer learning aims to improve the performance of target learners by transferring knowledge from related source domains, reducing the reliance on target-domain data. This survey aims to systematize and summarize existing research studies in order to help readers understand the current status and ideas in the area of transfer learning.

PROCEEDINGS OF THE IEEE (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Learning to Generate Fair Clusters from Demonstrations

Sainyam Galhotra et al.

Summary: Fair clustering is the process of grouping similar entities together while satisfying a mathematically defined fairness metric. The study focuses on identifying the fairness constraint from limited demonstrations by experts and presents algorithms to generate fair and interpretable clusters. The approach is also extended to novel fairness metrics and investigates how to produce interpretable solutions.

AIES '21: PROCEEDINGS OF THE 2021 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY (2021)

添加到收藏夹

Article Computer Science, Information Systems

An Overview of Fairness in Clustering

Anshuman Chhabra et al.

Summary: Clustering algorithms are crucial in modern data science, and fair clustering research lacks a comprehensive survey. This paper categorizes existing research and discusses future directions to provide researchers with an organized overview of the field and inspire new research in this area.

IEEE ACCESS (2021)

添加到收藏夹

Proceedings Paper Computer Science, Theory & Methods

Fair Clustering via Equitable Group Representations

Mohsen Abbasi et al.

Summary: This paper delves into the concept of group-representative clustering, aiming to ensure that cluster centers can equally represent different groups, thus enhancing fairness in clustering. It is found that this fairness concept parallels the development of fairness notions in classification, with some distinctions. Through approximation algorithms and empirical evaluations, the practical value of this concept is demonstrated.

PROCEEDINGS OF THE 2021 ACM CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, FACCT 2021 (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A Survey on Transfer Learning

Sinno Jialin Pan et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2010)

添加到收藏夹

Proving unfairness of decision making systems without model access

相关参考文献

How fair can we go in machine learning? Assessing the boundaries of accuracy and fairness

A Comprehensive Survey on Transfer Learning

Learning to Generate Fair Clusters from Demonstrations

An Overview of Fairness in Clustering

Fair Clustering via Equitable Group Representations

A Survey on Transfer Learning

导出引文

分享论文