wuliwei9278 / SSE-PT

Codes and Datasets for paper RecSys'20 "SSE-PT: Sequential Recommendation Via Personalized Transformer" and NurIPS'19 "Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers"
108 stars 18 forks source link

How to reproduction the SSE-PT model? #3

Open Li-fAngyU opened 2 years ago

Li-fAngyU commented 2 years ago

Thanks for this nice work! I follow README.md, install the required package and run:

python3 main.py

but the best performance achievable on ml1m dataset is HR@10 = 0.7569, NDCG@10 = 0.5040 which is lower than the result in paper. Is it possible my environment problem? Python: 3.6.13 , Tensorflow:1.15.4 image