search

HaoyueBai98 / MILK

[2024 SIGIR] Multimodality Invariant Learning for Multimedia-Based New Item Recommendation
0 stars 0 forks source link

complete dataset #1

Open zhouchengyi opened 2 months ago

zhouchengyi commented 2 months ago

This is a very interesting work, but when I tried to run the code, the system prompted that files such as cold_item_index.npy, warm_missing_item_index.npy, cold_missing_item_index.npy, image_feat_missing_test.npy, etc., were missing. Could you please provide the complete experimental dataset?

Additionally, I am not sure if there are any other issues in the code after downloading the complete dataset. I kindly ask if you could check to ensure that the code runs correctly upon direct download.

I look forward to your response!

HaoyueBai98 commented 2 months ago

Thank you for your interest! We use the cold start work earlier data sets, can be directly downloaded from here: https://github.com/CRIPAC-DIG/LATTICE.

The missing files are an index that randomly selects a certain percentage of items and can be obtained by simple data processing.

I uploaded a complete data set for reference (https://drive.google.com/file/d/1C-18Y84lMS5xsRGwKQYa9P0Tot-gxgYY/view?usp=sharing). Please feel free to contact me if you have any further questions.

Wish you all the best!