star-gcn's Introduction

STAR-GCN

The MXNet implementation of STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems in IJCAI 2019

Prerequisite

Requirements

MXNet Version 1.5.0
- Please build from source
- Compile the customized segment operator kernel according to README
GraphSampler
- Compile the graphsampler API according to README
GluonNLP

pip install gluonnlp

spaCy

pip install spacy
python -m spacy download en

Installation

Install the mxgraph python package

python setup.py develop

Training

The training scripts are in the experiments directory. The chosen hyperparameters are stored in yml files in the cfg dirctory.

For example, to train the MovieLens-100k in the transductive setting, we can run

cd experiments/cfg
python ../STAR-GCN.py --ctx gpu0 --cfg transductive_ml_100k.yml

Cite

Please cite our paper if you use this code in your own work:

@inproceedings{zhang2019star,
  title     = {STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems},
  author    = {Zhang, Jiani and Shi, Xingjian and Zhao, Shenglin and King, Irwin},
  booktitle = {The 28th International Joint Conference on Artificial Intelligence},
  pages     = {4264--4270},
  year      = {2019}
}

star-gcn's People

Contributors

Stargazers

Watchers

star-gcn's Issues

AttributeError: module 'mxnet.symbol.contrib' has no attribute 'seg_weighted_pool'

AttributeError: module 'mxnet.symbol.contrib' has no attribute 'seg_weighted_pool'
I can't find this function in the mxnet API ?

ImportError: cannot import name 'replace_file'

Hello,
I have the following error when trying to run the example given :

Traceback (most recent call last):
  File "../STAR-GCN.py", line 8, in <module>
    from mxgraph.datasets import LoadData
  File "/root/STAR-GCN/mxgraph/datasets.py", line 11, in <module>
    import gluonnlp as nlp
  File "/usr/local/lib/python3.5/dist-packages/gluonnlp/__init__.py", line 25, in <module>
    from . import data
  File "/usr/local/lib/python3.5/dist-packages/gluonnlp/data/__init__.py", line 23, in <module>
    from . import (batchify, candidate_sampler, conll, corpora, dataloader,
  File "/usr/local/lib/python3.5/dist-packages/gluonnlp/data/question_answering.py", line 31, in <module>
    from mxnet.gluon.utils import download, check_sha1, _get_repo_file_url, replace_file
ImportError: cannot import name 'replace_file'

A maybe similar issue was reported here : dmlc/gluon-nlp#1201 : it seems to come from an incompatibility between gluon and mxnet 1.5 ? Should I upgrade mxnet to 1.6 or would it cause issues with STAR-GCN training after ?

Thanks in advance !