We lifted 11 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| algowatchpenn/GerryFair | canonical | 1 of 5 |
| copy not recorded | — | 2 of 4 |
| sethneel/GerryFair | pwc_unofficial | 0 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| center | Ran | algowatchpenn/GerryFair/gerryfair/clean.py code served (permissive licence) · get_code("bf099d646e73cf6e") |
| gen_a | Ran | this paper's copy was not recorded; identical code first harvested from wibrown/GerryFair pointer only · get_code("b2afbc4ac64576bb") |
| learner_costs | Ran | this paper's copy was not recorded; identical code first harvested from wibrown/GerryFair pointer only · get_code("791852801122e9e5") |
| calc_disp | Not yet run | algowatchpenn/GerryFair/gerryfair/heatmap.py code served (permissive licence) · get_code("d475d39df96fac45") |
| clean_dataset | Not yet run | algowatchpenn/GerryFair/gerryfair/clean.py code served (permissive licence) · get_code("cd537de833dfde8f") |
| clean_dataset | Not yet run | sethneel/GerryFair/gerryfair/clean.py code served (permissive licence) · get_code("8adf5d639ebb5df1") |
| get_fp | Not yet run | this paper's copy was not recorded; identical code first harvested from wibrown/GerryFair pointer only · get_code("e1efab7d887f28a5") |
| get_group | Not yet run | this paper's copy was not recorded; identical code first harvested from wibrown/GerryFair pointer only · get_code("bedf19c17f580dd6") |
| heat_map | Not yet run | algowatchpenn/GerryFair/gerryfair/heatmap.py code served (permissive licence) · get_code("f9a1bd2d964a57e2") |
| one_hot_code | Not yet run | algowatchpenn/GerryFair/gerryfair/clean.py code served (permissive licence) · get_code("97207ff93fd80888") |
| plot_pareto | Not yet run | sethneel/GerryFair/gerryfair/fairness_plots.py code served (permissive licence) · get_code("d17910bf14c509ca") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Kearns et al. [2018] recently proposed a notion of rich subgroup fairness intended to bridge the gap between statistical and individual notions of fairness. Rich subgroup fairness picks a statistical fairness constraint (say, equalizing false positive rates across protected groups), but then asks that this constraint hold over an exponentially or infinitely large collection of subgroups defined by a class of functions with bounded VC dimension. They give an algorithm guaranteed to learn subject to this constraint, under the condition that it has access to oracles for perfectly learning absent a fairness constraint. In this paper, we undertake an extensive empirical evaluation of the algorithm of Kearns et al. On four real datasets for which fairness is a concern, we investigate the basic convergence of the algorithm when instantiated with fast heuristics in place of learning oracles, measure the tradeoffs between fairness and accuracy, and compare this approach with the recent algorithm of Agarwal et al. [2018], which implements weaker and more traditional marginal fairness constraints defined by individual protected attributes. We find that in general, the Kearns et al. algorithm converges quickly, large gains in fairness can be obtained with mild costs to accuracy, and that optimizing accuracy subject only to marginal fairness leads to classifiers with substantial subgroup unfairness. We also provide a number of analyses and visualizations of the dynamics and behavior of the Kearns et al. algorithm. Overall we find this algorithm to be effective on real data, and rich subgroup fairness to be a viable notion in practice.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1808.08166")
get_code_for_paper("1808.08166")
have("1808.08166")
Connect an agent — have() is free.