recommenders icon indicating copy to clipboard operation
recommenders copied to clipboard

[ASK] Using datasets with a large number of users such as Gowalla in LightGCN model, RAM gets a lot involved

Open Sepiiiideh opened this issue 2 years ago • 1 comments

I'm using google colab for training the model. I used gowalla dataset and after a few seconds after calling model = LightGCN(hparams, data, seed=SEED) System RAM gets full and my session terminates. I think this happens when creating adjacency matrix what should I do to fix this?

Sepiiiideh avatar Apr 07 '22 17:04 Sepiiiideh

Hi @Sepiiiideh , you have passed your data set in chunk size for training . I think, your dataset is too large. so that, processor should not be perform task at time.

RanjanRavi2398 avatar Dec 06 '22 09:12 RanjanRavi2398