Group fairness in non-monotone submodular maximization

Maximizing a submodular function has a wide range of applications in machine learning and data mining. One such application is data summarization whose goal is to select a small set of representative and diverse data items from a large dataset. However, data items might have sensitive attributes suc...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of combinatorial optimization Ročník 45; číslo 3; s. 88
Hlavní autoři: Yuan, Jing, Tang, Shaojie
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.04.2023
Springer Nature B.V
Témata:
Algorithms
Approximation
Combinatorics
Constraints
Convex and Discrete Geometry
Data mining
Decision making
Feature selection
Machine learning
Mathematical Modeling and Industrial Mathematics
Mathematics
Mathematics and Statistics
Maximization
Operations Research/Decision Theory
Optimization
S.I. : AAIM 2022
Theory of Computation
Utility functions
Approximation algorithm
Submodular optimization
Group fairness
ISSN:1382-6905, 1573-2886
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Maximizing a submodular function has a wide range of applications in machine learning and data mining. One such application is data summarization whose goal is to select a small set of representative and diverse data items from a large dataset. However, data items might have sensitive attributes such as race or gender, in this setting, it is important to design fairness-aware algorithms to mitigate potential algorithmic bias that may cause over- or under- representation of particular groups. Motivated by that, we propose and study the classic non-monotone submodular maximization problem subject to novel group fairness constraints. Our goal is to select a set of items that maximizes a non-monotone submodular function, while ensuring that the number of selected items from each group is proportionate to its size, to the extent specified by the decision maker. We develop the first constant-factor approximation algorithms for this problem. We also extend the basic model to incorporate an additional global size constraint on the total number of selected items.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1382-6905
1573-2886
DOI:10.1007/s10878-023-01019-4