This library contains a MindSpore implementation of 'Task-Adversarial-Adaptation-for-Multi-modal-Recommendation'
-
AliExpressDataset: This is a dataset gathered from real-world traffic logs of the search system in AliExpress. This dataset is collected from 5 countries: Russia, Spain, French, Netherlands, and America, which can utilized as 5 multi-task datasets. Original_dataset Processed_dataset Google Drive Processed_dataset Baidu Netdisk
You can put the downloaded '.zip' files in
./data/
and runpython preprocess.py --dataset_name NL
to process the dataset.
- Python>=3.7
- Mindspore==2.1.1
- pandas
- numpy
- tqdm
You can run a model through:
python main.py --model_name aitm --tgt_dataset_name AliExpress_US