Skip to search boxSkip to navigationSkip to main content

Fairness in network representation by latent structural heterogeneity in observational data

Output:
Chapter in Book/Report/Conference proceeding
Conference contribution
Academic
Peer-review

Open access

Information

Output type

Output:
Chapter in Book/Report/Conference proceeding
Conference contribution
Academic
Peer-review

Original language

English

Article number

5792

Pages 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 Alto

Publisher

AAI Press

Publication series

  • Publication series name: Proceedings of the AAAI Conference on Artificial Intelligence
    Volume: 34
    Number: 4
978-1-57735-835-0

ISBN (Electronic)

9781577358350

Host 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

Conference

Degree of recognition

International event

Date

07/02/2020 - 12/02/2020

Location

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.

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