search

RUCAIBox / RecBole

A unified, comprehensive and efficient recommendation library
https://recbole.io/
MIT License
3.4k stars 612 forks source link

[šŸ’”SUG] Can you include further models? #2101

Open jindeok opened 3 hours ago

jindeok commented 3 hours ago

Hi RecBole Team!

In SIGIR'24, we've published an paper called Turbo-CF (Park et al., "Turbo-cf: Matrix decomposition-free graph filtering for fast recommendation." In SIGIR 2024). This is graph filtering-based, extremely simple to implement, yet powerful recommendation method. It only requires few lines of code for end-to-end running.

We would greatly appreciate it if the RecBole team could consider adding Turbo-CF to the RecBole model. This would enable more researchers and practitioners to easily access and apply this model for their recommendation tasks. Refer to my code here: https://github.com/jindeok/Turbo-CF

Thank you for your time and consideration :)

Fotiligner commented 2 hours ago

Thank you for your interest in RecBoleļ¼ We welcome you to submit PR in the github repository. You could refer to our previous model files.