Codes for SIGIR 2020 paper CATN: Cross-Domain Recommendation for Cold-Start Users via Aspect Transfer Network.
Please cite our paper if you find this code useful for your research:
@inproceedings{sigir20:catn,
author = {Cheng Zhao and
Chenliang Li and
Rong Xiao and
Hongbo Deng and
Aixin Sun},
title = {{CATN:} Cross-Domain Recommendation for Cold-Start Users via Aspect
Transfer Network},
booktitle = {{SIGIR}},
year = {2020},
}
- python 3.6
- tensorflow 1.10.0
- numpy
- pandas
- scipy
- gensim
- sklearn
- tqdm
dataset/
preprocessing.py
: constructing cross-domain datasets;
runner/
CATN_runner.py
: the main runner (including the configurations);
utils
CATN.py
: CATN implementation.
-
Download the original data from Amazon-5core, choose two relevant categories (e.g., Books, Movies and TV) and put them under the same directory in dataset/.
-
run python preprocessing.py.
-
run python CATN_runner.py.