ashudeep / fair-pgrank Goto Github PK

Hello ashudeep,
Thank you for your implementation and I am very interested in your work. When I run the code on another dataset, it occurs that

Traceback (most recent call last):
File "train_amazon_dataset.py", line 608, in
args=args)
File "train_amazon_dataset.py", line 244, in on_policy_training
args=args)
File "train_amazon_dataset.py", line 58, in log_and_print
args=args)
File "/raid/user_storage/host/Fair-PGRank/evaluation.py", line 194, in evaluate_model
feats, rel = convert_vars_to_gpu([feats, rel], gpu_id)
File "/raid/user_storage/host/Fair-PGRank/models.py", line 117, in convert_vars_to_gpu
return [var.to(device) for var in varlist]
File "/raid/user_storage/host/Fair-PGRank/models.py", line 117, in
return [var.to(device) for var in varlist]
AttributeError: 'numpy.ndarray' object has no attribute 'to'

could you give me some advice to solve it?
Thank yo so much!
Best,
Xiuling

Hello ashudeep,

I read your paper
https://papers.nips.cc/paper/8782-policy-learning-for-fairness-in-ranking
and I am impressed with your idea and would like to do research based on this paper.
However, there are two things I don't understand after reading your paper.

1. When calculating the fairness of individual i, I think the following formula is used.
   exposure (i) / merit (i)
   But how do you calculate if the denominator merit (i) is 0 in implicit feedback?

2. Should fairness be calculated against the overall ranking?
   In general, people will use the top k(<<n) rankings for n items.
   Do you need to calculate group fairness for all n items, not just top k?
   In other words, is it a fair ranking if groups A and B have the following for the items in top k only?
   group exposure(A) / group merit(A)
   = group exposure(B) / group merit(B)

When I read your paper, it seems to me that you are doing the math for every item...

Thank you