Closed liuhu-bigeye closed 4 years ago
Reimplementation with the metric in the paper results in a lot higher score, e.g. Amazon Electro: 0.9776. So I guess the AUC defined in the paper is not correct and other works should not use this metric to make fair comparison with the paper.
Reimplementation with the metric in the paper results in a lot higher score, e.g. Amazon Electro: 0.9776. So I guess the AUC defined in the paper is not correct and other works should not use this metric to make fair comparison with the paper.
because in their test set, each user only has one positive sample and one negative sample, the number of impressions for each user in the test set are the same, hence gauc == average auc
Thanks for answering
In the paper, 'AUC' is defined as: .
However, the two metrics provided in the code are: and .
Please correct me if I misunderstand the code.