Problems of results of LightGCN about qrec HOT 4 CLOSED

For SEPT, the best results are reported because after each epoch, the immediate results are recored.

For LightGCN, you can use the same way to get the best performance. According to my experience, LightGCN needs hundreds of epochs to get converged. The way to speedup the training is applying L2 normalization at each layer.

The results reported in the paper were based on python 2. We later upgraded QRec and transplated it to python3. So, there would be some trivial differences on performance. We conducted 5-fold cross-validation. Not sure if you applied the same experimental setting. BTW, you can try our pytorch implementation of LightGCN at https://github.com/Coder-Yu/SELFRec/blob/main/model/graph/LightGCN.py

from qrec.

Thank you for your reply.

I just find changing reduce_mean to reduce_sum in LightGCN as SEPT can make the original LightGCN behave similarly as SEPT in the early training phase. I think this may be the reason.

Thank you for your time and great repo!

from qrec.

"changing reduce_mean to reduce_sum in LightGCN as SEPT can make the original LightGCN behave similarly as SEPT in the early training phase"

Exactly. I forgot to pinpoint this cause. I wish you a good luck on your study.

from qrec.

Thanks a lot!

from qrec.