Open Hamedloghmani opened 1 year ago
@Hamedloghmani Any progress with any of these tasks?
@hosseinfani Yes, these are the stuff that are going to be reported by the end of the day:
These are next in the queue:
@Hamedloghmani how about equality of odds implementation?
@hosseinfani My understanding from demographic parity, equality of opportunity and equalized odds is that if we want to include equalized odds or equality of opportunity, we have to somehow enter a label to our problem to define whether an expert is 'qualified' or not. And then examine how qualified/non-qualified experts place into the team. I think ( with my knowledge at this point, I might be wrong) these are not suitable for our problem and demographic parity which falls under group fairness criteria is more helpful.
My personal suggestion is going with Group/Individual fairness criteria instead of the 3 that I mentioned at the beginning since most of the significant work in fairness did the same.
I would be happy to hear your input on this. I can dedicate more time to equalized odds if you believe it would be helpful for us.
@Hamedloghmani I update the tasks. Please come up with a timeline in this issue page (don't create another doc/issue). Also, drop by during office hour every week to discuss your progress.
@Hamedloghmani pls keep this issue page updated with your fall23 plan.
@hosseinfani Sure, the page has been successfully updated with the tasks that we discussed and you kindly mentioned in our Excel sheet.
The plan for both short and long term future development of this project will be discussed here. This is just a road map to have a bird's-eye view on the project and each task should be defined in details in another issue page if needed. In case a separate issue page is created for a task, it should be linked here by the number of created issue.
1- Experiments
2- Implementation:
3- Refactor
4- Write up and literature review
Done:
#######################
###################################################################
###################################################################
[x] Demographic Parity.popularity.0.05.100.fa-ir.ndkl.imdb
[x] Demographic Parity.popularity.0.05.100.fa-ir.skew.imdb
[x] Demographic Parity.popularity.0.05.100.fa-ir.ndkl.dblp
[x] Demographic Parity.popularity.0.05.100.fa-ir.skew.dblp
[x] Demographic Parity.gender.0.05.100.fa-ir.ndkl.imdb
[x] Demographic Parity.gender.0.05.100.fa-ir.skew.imdb
[x] Demographic Parity.gender.0.05.100.fa-ir.ndkl.dblp (compute canada)
[x] Demographic Parity.gender.0.05.100.fa-ir.skew.dblp (compute canada)
[x] Demographic Parity.popularity.0.01.100.fa-ir.ndkl.imdb
[x] Demographic Parity.popularity.0.01.100.fa-ir.skew.imdb
[x] Demographic Parity.popularity.0.01.100.fa-ir.ndkl.dblp
[x] Demographic Parity.popularity.0.01.100.fa-ir.skew.dblp
[x] Demographic Parity.gender.0.01.100.fa-ir.ndkl.imdb
[x] Demographic Parity.gender.0.01.100.fa-ir.skew.imdb
[x] Demographic Parity.gender.0.01.100.fa-ir.ndkl.dblp
[x] Demographic Parity.gender.0.01.100.fa-ir.skew.dblp #########################################################################
[x] Demographic Parity.Popularity.Greedy.IMDB ( due 4/28/2023)
[x] Demographic Parity.Popularity.GreedyConservative.IMDB ( due 4/28/2023)_
[x] Demographic Parity.Popularity.GreedyRelaxed.IMDB ( due 4/28/2023)_
[x] Equality of Opportunity.Popularity.Greedy.IMDB ( due 4/28/2023)
[x] Equality of Opportunity.Popularity.Greedy_Conservative.IMDB
[x] Equality of Opportunity.Popularity.GreedyRelaxed.IMDB ( due 4/28/2023)_
[x] Demographic Parity.Gender.Greedy.IMDB
[x] Demographic Parity.Gender.Greedy_Conservative.IMDB
[x] Demographic Parity.Gender.Greedy_Relaxed.IMDB
[x] Demographic Parity.Popularity.Greedy.DBLP
[x] Demographic Parity.Popularity.Greedy_Conservative.DBLP
[x] Demographic Parity.Popularity.Greedy_Relaxed.DBLP
[x] Equality of Opportunity.Popularity.Greedy.DBLP
[x] Equality of Opportunity.Popularity.Greedy_Conservative.DBLP
[x] Equality of Opportunity.Popularity.Greedy_Relaxed.DBLP
[x] averaging methods for fairness outputs such as skew and ndkl for different folds
[x] Full paper writeup for ECIR ir for good
[x] Resource paper writeup
[x] Fair Top-k Ranking with multiple protected groups
[x] Add FA*IR: A Fair Top-k Ranking Algorithm to the pipeline #80
[x] Add another fairness metric e.g. skew (or from normalized discounted difference (rND), ratio (rRD), and KL-divergence (rKL) proposed in Measuring Fairness in Ranked Outputs)
[x] FA*IR: A Fair Top-k Ranking Algorithm ( due 4/28/2023)
[x] Clean and push equality of opportunity function ( due 4/28/2023)
[x] Inferring the gender labels for DBLP dataset #36
[x] Inferring the gender labels for IMDB dataset #36
[x] Collect and process GitHub dataset
[x] Explore papers for other state-of-the-art score-based ranking and learning to rank methods