search

zyang1580 / CoLLM

The implementation for the work "CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation".
BSD 3-Clause "New" or "Revised" License
47 stars 6 forks source link

hot and cold datasets #9

Closed NicholasEinstein closed 1 week ago

NicholasEinstein commented 3 months ago

Hello author, I noticed that your code does not seem to provide the hot and cold datasets mentioned in the paper. Is it missing? Sincerely looking forward to your supplementation

zyang1580 commented 3 months ago

Thank you for your question. There is no need for an additional hot and cold dataset. You can directly obtain the hot and cold data by filtering the "not_cold" (or "warm") field. Please refer to the code [here].(https://github.com/zyang1580/CoLLM/blob/1ac29077d885cfeb179ee57a972d99580946b687/minigpt4/datasets/datasets/rec_datasets.py#L444)