rank loss func bug - Githubissues

fulifeng / Temporal_Relational_Stock_Ranking

Code for paper "Temporal Relational Ranking for Stock Prediction"

https://arxiv.org/pdf/1809.09441.pdf

GNU Affero General Public License v3.0

438 stars 164 forks source link

Open MLightM opened 3 years ago

MLightM commented 3 years ago

rank loss should be ''..... - tf.multiply(pre_pw_dif, gt_pw_dif) ...‘’, '-' is missing when define the loss in rank_lstm.py

fulifeng commented 3 years ago

Come on! Please check the difference when we calculate: pre_pw_dif and gt_pw_dif

MLightM commented 3 years ago

Come on! Please check the difference when we calculate: pre_pw_dif and gt_pw_dif

oh... yes, you are right, thanks!

wjhmike95 commented 2 years ago

why do you use "mean" to reduce rank loss instead of "sum" which is from loss equation in the essay?

ownnaruto commented 10 months ago

Is this loss really useful？I try so many times, just find that the results without rank loss are much better!