SCoRe
SCoRe copied to clipboard
SCoRe is a sequential recommendation model with dual side neighbor-based collaborative filtering. Implementation of our WSDM 2020 paper.
Results
2
SCoRe issues
Sort by
recently updated
recently updated
newest added
great code and paper, thanks only can you help download data since these links are behind registration wall https://tianchi.aliyun.com/dataset/dataDetail?dataId=649 https://tianchi.aliyun.com/dataset/dataDetail?dataId=42
为什么train_score.py里的TRAIN_NEG_SAMPLE_NUM = 1,TEST_NEG_SAMPLE_NUM = 49,论文里写的不是使用100个负例吗,同时采样时也采样了100个,那么train_score.py里为什么设置这样呢?