Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update README.md #4

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update README.md #4

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
4 changes: 4 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,7 @@
Note that there is a recent paper "Performance comparison of neural and non-neural approaches to session-based recommendation" arguing that NextItNet produces worse result than GRU4Rec and Caser, and run slowly during training. We have consulted with the author regarding this issue. The author replied us this is because of the session length problem. For example, if you use session length (i.e., window size) 20 for Caser but using 500 for NextItNet (the authors performed experiments in this way), then there will be 480 zeros padded, which will be very slow during training. Besides, using relatively smaller sessions also means you have more training sequences and thus will get better results if your dataset is not large enough.
==================



strongly suggest running the code on GPU, which is at least 20 times faster than on CPU.
You can email me if you have any questions about the performance and efficiency of NextItNet.
Expand Down