Original implementation for paper Exploring Periodicity and Interactivity in Multi-Interest Framework for Sequential Recommendation.
Accepted to IJCAI 2021!
- python 3.7
- tensorflow-gpu 1.13
- faiss-gpu 1.6.3
- numpy 1.19.2
- tensorboardX 2.1
- Install faiss-gpu based on the instructions here: https://github.com/facebookresearch/faiss/blob/master/INSTALL.md
-
Original links of datasets are:
-
You can download the original datasets and preprocess them by yourself. You can run
python preprocess/data.py {dataset_name}
andpython preprocess/category.py {dataset_name}
to preprocess the datasets. Note the illegal timestamp.
You can use python main.py --dataset {dataset_name} --time_span {time_threshold}
to train a specific model on a dataset. Other hyperparameters can be found in the code. (If you share the server with others or you want to use the specific GPU(s), you may need to set CUDA_VISIBLE_DEVICES
.)
For example, you can use python main.py --dataset book --time_span 64
to train PIMI model on Book dataset.
The structure of our code is based on ComiRec.