Fairness in network representation by latent structural heterogeneity in observational data
Output:
Chapter in Book/Report/Conference proceeding
Conference contribution
Academic
Peer-reviewOpen access
Information
Output type
Output:
Chapter in Book/Report/Conference proceeding
Conference contribution
Academic
Peer-reviewOriginal language
EnglishArticle number
5792Pages from-to (Number of pages)
Pages 3809-3816 (8 pages)Publication milestones
- Published - 03/04/2020
Publication status
Published - 03/04/2020
Place of publication
Palo AltoPublisher
AAI PressPublication series
- Publication series name: Proceedings of the AAAI Conference on Artificial Intelligence
Volume: 34
Number: 4
ISBN (Print)
978-1-57735-835-0 ISBN (Electronic)
9781577358350Host publication title
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020)Related Event
Title
34th AAAI conference on Artificial Intelligence, AAAI 2020
Event type
ConferenceDegree of recognition
International eventDate
07/02/2020 - 12/02/2020Location
Hilton New York MidtownNew YorkUnited States
Abstract
While recent advances in machine learning put many focuses on fairness of algorithmic decision making, topics about fairness of representation, especially fairness of network representation, are still underexplored. Network representation learning learns a function mapping nodes to low-dimensional vectors. Structural properties, e.g. communities and roles, are preserved in the latent embedding space. In this paper, we argue that latent structural heterogeneity in the observational data could bias the classical network representation model. The unknown heterogeneous distribution across subgroups raises new challenges for fairness in machine learning. Pre-defined groups with sensitive attributes cannot properly tackle the potential unfairness of network representation. We propose a method which can automatically discover subgroups which are unfairly treated by the network representation model. The fairness measure we propose can evaluate complex targets with multi-degree interactions. We conduct randomly controlled experiments on synthetic datasets and verify our methods on real-world datasets. Both quantitative and quantitative results show that our method is effective to recover the fairness of network representations. Our research draws insight on how structural heterogeneity across subgroups restricted by attributes would affect the fairness of network representation learning.
Documents and Links
Metrics
Metrics
SciVal
FWCI
0.40
SciVal
Author count
4
SciVal
Paper percentile
48
SciVal
citations
9
Scopus
citations
9
PlumX, opens in new tab
Citation count
9
Captures
22
