Recommendation model for CTR prediction
Closed projects. The performance is no better than LightGCN(Xiangnan He)
-
https://github.com/LunaBlack/KGAT-pytorch # model KGAT Pyorch implementation
-
https://github.com/xiangwang1223/knowledge_graph_attention_network # model KGAT Tensorflow implementation
-
https://github.com/gusye1234/LightGCN-PyTorch # model LightGCN Pyorch implementation
-
https://github.com/shenweichen/GraphEmbedding # a lot of graph embedding model (DeepWalk, Struc2Vec, etc.) implementation
The code has been tested running under Python 3.6.8. The required packages are as follows:
If you want to use GPU, you should install cuda-version of torch & dgl
- torch
- dgl
- numpy
- pandas
- scipy
- sklearn
- networkx
- fastdtw
- joblib