cripac-dig / tagnn

[SIGIR 2020] Python implementation for "TAGNN: Target Attentive Graph Neural Networks for Session-based Recommendation"

TAGNN

This is the code for the SIGIR 2020 Paper: TAGNN: Target Attentive Graph Neural Networks for Session-based Recommendation.

Usage

Requirements

Citation

Please cite our paper if you use the code:

@inproceedings{yu2020tagnn,
  title={TAGNN: Target attentive graph neural networks for session-based recommendation},
  author={Yu, Feng and Zhu, Yanqiao and Liu, Qiang and Wu, Shu and Wang, Liang and Tan, Tieniu},
  booktitle={Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval},
  pages={1921--1924},
  year={2020}
}

tagnn's Issues

What is the experimental environment？

Graphic Memory problems

When running with dataset DIGINETICA, I found this program is really memory demanding, not to speak of YOOCHOOSE. For my case, one TITAN XP is just not enough. Then I was trying to apply multi graph cards to cuda and I just failed to do so.
I try to use Dataparallel from torch:

os.environ['CUDA_VISIBLE_DEVICES'] = '0,1'
model = torch.nn.Dataparallel(SessionGraph())
model = model.cuda()

Since model is now a DataParallel object the parameters in train_test is modified accordingly

model.loss_function → model.module.loss_function
...

And that didn't work. I still got runtime error about not enough memory in GPU0 while GPU1 was barely utilized. So I want to know how you guys done it. Great thanks in advance!

Please publish the code

We are very interest in TAGNN work. But we fail to reproduce the results of TAGNN in SIGIR2020, please publish the code.

When will the code be available?