This is the implementation of our NeurIPS 2023 paper:

Zhengyi Yang, Jiancan Wu, Zhicai Wang, Xiang Wang, Yancheng Yuan, and Xiangnan He. Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion. In NeurIPS 2023. arXiv

python -u DreamRec.py --data yc --timesteps 500 --lr 0.001 --beta_sche exp --w 2 --optimizer adamw --diffuser_type mlp1 --random_seed 100

python -u DreamRec.py --data ks --timesteps 2000 --lr 0.00005 --beta_sche cosine --w 2 --optimizer adamw --diffuser_type mlp1 --random_seed 100

python -u DreamRec.py --data zhihu --timesteps 500 --lr 0.01 --beta_sche linear --w 4 --optimizer adamw --diffuser_type mlp1 --random_seed 100 

In our more recent work RecInterpreter arXiv, the oracle items generated by DreamRec can be instantiated by Large Language Models with textual descriptions. Please refer to the paper for more details!