Advanced search
1 file | 703.96 KB Add to list

DeBayes : a Bayesian method for debiasing network embeddings

Maarten Buyl (UGent) and Tijl De Bie (UGent)
(2020)
Author
Organization
Abstract
As machine learning algorithms are increasingly deployed for high-impact automated decision making, ethical and increasingly also legal standards demand that they treat all individuals fairly, without discrimination based on their age, gender, race or other sensitive traits. In recent years much progress has been made on ensuring fairness and reducing bias in standard machine learning settings. Yet, for network embedding, with applications in vulnerable domains ranging from social network analysis to recommender systems, current options remain limited both in number and performance. We thus propose DeBayes: a conceptually elegant Bayesian method that is capable of learning debiased embeddings by using a biased prior. Our experiments show that these representations can then be used to perform link prediction that is significantly more fair in terms of popular metrics such as demographic parity and equalized opportunity.
Keywords
DeBayes, debias, fairness, network embedding, link prediction, graph embedding, conditional network embedding, cne

Downloads

  • debayes.pdf
    • full text (Author's original)
    • |
    • open access
    • |
    • PDF
    • |
    • 703.96 KB

Citation

Please use this url to cite or link to this publication:

MLA
Buyl, Maarten, and Tijl De Bie. DeBayes : A Bayesian Method for Debiasing Network Embeddings. 2020.
APA
Buyl, M., & De Bie, T. (2020). DeBayes : a Bayesian method for debiasing network embeddings.
Chicago author-date
Buyl, Maarten, and Tijl De Bie. 2020. “DeBayes : A Bayesian Method for Debiasing Network Embeddings.”
Chicago author-date (all authors)
Buyl, Maarten, and Tijl De Bie. 2020. “DeBayes : A Bayesian Method for Debiasing Network Embeddings.”
Vancouver
1.
Buyl M, De Bie T. DeBayes : a Bayesian method for debiasing network embeddings. 2020.
IEEE
[1]
M. Buyl and T. De Bie, “DeBayes : a Bayesian method for debiasing network embeddings.” 2020.
@misc{8649561,
  abstract     = {As machine learning algorithms are increasingly deployed for high-impact automated decision making, ethical and increasingly also legal standards demand that they treat all individuals fairly, without discrimination based on their age, gender, race or other sensitive traits. In recent years much progress has been made on ensuring fairness and reducing bias in standard machine learning settings. Yet, for network embedding, with applications in vulnerable domains ranging from social network analysis to recommender systems, current options remain limited both in number and performance. We thus propose DeBayes: a conceptually elegant Bayesian method that is capable of learning debiased embeddings by using a biased prior. Our experiments show that these representations can then be used to perform link prediction that is significantly more fair in terms of popular metrics such as demographic parity and equalized opportunity.},
  author       = {Buyl, Maarten and De Bie, Tijl},
  keywords     = {DeBayes,debias,fairness,network embedding,link prediction,graph embedding,conditional network embedding,cne},
  language     = {eng},
  pages        = {9},
  title        = {DeBayes : a Bayesian method for debiasing network embeddings},
  year         = {2020},
}