search

yusanshi / news-recommendation

Implementations of some methods in news recommendation.
MIT License
241 stars 50 forks source link

Did you remove FIM？ #3

Closed jiaqinglin closed 3 years ago

jiaqinglin commented 3 years ago

Can you share your basic results over these models? I rememberd that there was a FIM implement. But you did not show the results.

yusanshi commented 3 years ago

Did you remove FIM?

Yes I found there are some errors in my implementation but I have no time to fix it. So I just removed it. You can view it in the commit history.

Can you share your basic results over these models?

Months ago, I tested all the methods on MIND small dataset and shown the results in README.md. However, I have made some small changes to the code and I began to use MIND large dataset. So I removed the outdated results. Sorry but I haven't tested on the new code and new dataset.

Veason-silverbullet commented 3 years ago

Hi, @yusanshi ,

Many thanks for your code! Can you share your finding of FIM? Is it comparable to other strong baselines,i.e., NRMS/NAML? I doubt its performance as my implementation of FIM cannot achieve the expected performance.

yusanshi commented 3 years ago

Hi @Veason-silverbullet

Yes, my implementation for FIM didn't work well too. Not knowing whether there are some errors with my code I just removed it :(