deepctr.models.deepfm module

Weichen Shen,
[1] Guo H, Tang R, Ye Y, et al. Deepfm: a factorization-machine based neural network for ctr prediction[J]. arXiv preprint arXiv:1703.04247, 2017.(
deepctr.models.deepfm.DeepFM(feature_dim_dict, embedding_size=8, use_fm=True, hidden_size=(128, 128), l2_reg_linear=1e-05, l2_reg_embedding=1e-05, l2_reg_deep=0, init_std=0.0001, seed=1024, keep_prob=1, activation='relu', final_activation='sigmoid', use_bn=False)[source]

Instantiates the DeepFM Network architecture.

  • feature_dim_dict – dict,to indicate sparse field and dense field like {‘sparse’:{‘field_1’:4,’field_2’:3,’field_3’:2},’dense’:[‘field_4’,’field_5’]}
  • embedding_size – positive integer,sparse feature embedding_size
  • use_fm – bool,use FM part or not
  • hidden_size – list,list of positive integer or empty list, the layer number and units in each layer of deep net
  • l2_reg_linear – float. L2 regularizer strength applied to linear part
  • l2_reg_embedding – float. L2 regularizer strength applied to embedding vector
  • l2_reg_deep – float. L2 regularizer strength applied to deep net
  • init_std – float,to use as the initialize std of embedding vector
  • seed – integer ,to use as random seed.
  • keep_prob – float in (0,1]. keep_prob used in deep net
  • activation – Activation function to use in deep net
  • final_activation – str,output activation,usually 'sigmoid' or 'linear'
  • use_bn – bool. Whether use BatchNormalization before activation or deep net

A Keras model instance.