Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Concepts on AI Fairness

Concepts on AI Fairness

Avatar for Yoriyuki Yamagata

Yoriyuki Yamagata

March 05, 2020
Tweet

More Decks by Yoriyuki Yamagata

Other Decks in Technology

Transcript

  1. Group discrimination vs. Individual discrimination • Group discrimination • eg.

    Men are more/less hired than women • Individual discrimination • eg. A man/woman with same skill is hired while a woman /man is not • Can be contradictory
  2. Motivating Example • Gender discrimination on employment • Men may

    be hired more/less likely than women • Extreme measure: hire 50/50% of men/women • The extreme measure may cause individual discrimination • Women with the same skill may be more/less likely hired than men
  3. Direct discrimination vs. indirect discrimination • Direct discrimination • eg.

    Hire employers based on gender • Indirect discrimination • eg. Hire based on features which correlated to gender
  4. Motivating example • Hire people with longer experience of full-time

    employment • This can be legitimate • Full-time employment may indicate higher skill • But can adversely affect women • Women tend to have more part-time job • Family responsibility, child birth, etc...
  5. General settings • S: sensitive features (gender, nationality, religion...) •

    X: other features • Y: output of the algorithm • Can be deterministic/probabilistic • Assume Y: binary
  6. Direct / Indirect discrimination • Fairness against direct discrimination •

    Pr[ Y = 1 | X, S ] = Pr[ Y = 1 | X ] • Fairness against indirect discrimination • Pr[ Y = 1 | S ] = Pr[ Y = 1 ] • X0: explainable feature • Pr[ Y = 1 | X0, S ] = Pr[ Y = 1 | X0 ]
  7. Motivating examples • Fairness against direct discrimination • Hire regardless

    of gender if an applicant has the same skill • Fairness against indirect discrimination • If 25% of applicants are women, 25% of hired applicants are also women (regardless of relative skill level between men/women)
  8. Problem of group fairness • Hire men by their skill,

    but women by the length of hair • Hire men randomly, but women by their skill • Probability can be same • More generally, it is based on statistical properties • address “disparate impact” • do not address “disparate treatment”
  9. Idea • “Similar” person (for a given task) must be

    treated similarly • eg. A person with the same skill level is treated in the same way, regardless of gender
  10. Formal setting • V : set of individual (= X,

    S) • Y : outcome (Y = 0 or 1) • d : similarity measure on V (real number) • d(x, y) >= 0, d(x, y) = d(y, x), d(x, x) = 0 • M : Assignment for Y to V (M : V -> distributions on Y) • may use lottery (eg. choosing jury) • D : measure of difference between two distribution on Y
  11. (D, d) - Lipschitz property • D(Mx, My) <= d(x,

    y) for all pairs of individuals x, y • • Dtv (P, Q) = 1 2 ∑ Y=0,1 |P(Y) − Q(Y)| D∞ (P, Q) = sup Y=0,1 log(max{ P(Y) Q(Y) , Q(Y) P(Y) })
  12. Relation to group fairness • : Average provability of Y

    = 1 for an individual belonging to S • : the largest for any M with (D, d) - Lipschitz property • Theorem: • : Earth mover’s distance between S and T μS (1) biasD,d (S, T) μS (1) − μT (1) biasD,d (S, T) ≤ dEM (S, T) dEM (S, T)
  13. Reflective equilibrium • Methodology of modern ethics • Start from

    intuition • Find a governing principle • Explanatory power • Internal consistency • consistency with other principles • Change intuition Principle Intuition
  14. When does distinction become discrimination? • Competing views (* are

    popular views) • If it causes disadvantage to one of the groups* • If it shows/expresses exclusion of one of the groups* • If it is not justified rationally • If it is based on one’s nature which cannot be changed
  15. References • ػցֶशɾσʔλϚΠχϯάʹ͓͚Δެฏੑ, Kamishima & Komiyama, ਓ޻஌ೳ34ר2߸, 2019 • Fairness

    Through Awareness, Dwork et al., ITCS 2012 • FlipTest: Fairness Testing via Optimal Transport, Black et al. ACM FAT 2020 • Altman, "Discrimination", The Stanford Encyclopedia of Philosophy (Winter 2016 Edition)