Features¶
Feature Columns¶
SparseFeat¶
SparseFeat is a namedtuple with signature SparseFeat(name, vocabulary_size, embedding_dim, use_hash, dtype, embeddings_initializer, embedding_name, group_name, trainable)
name : feature name
vocabulary_size : number of unique feature values for sprase feature or hashing space when
use_hash=Trueembedding_dim : embedding dimension
use_hash : defualt
False.IfTruethe input will be hashed to space of sizevocabulary_size.dtype : default
int32.dtype of input tensor.embeddings_initializer : initializer for the
embeddingsmatrix.embedding_name : default
None. If None, the embedding_name will be same asname.group_name : feature group of this feature.
trainable: default
True.Whether or not the embedding is trainable.
DenseFeat¶
DenseFeat is a namedtuple with signature DenseFeat(name, dimension, dtype)
name : feature name
dimension : dimension of dense feature vector.
dtype : default
float32.dtype of input tensor.
VarLenSparseFeat¶
VarLenSparseFeat is a namedtuple with signature VarLenSparseFeat(sparsefeat, maxlen, combiner, length_name, weight_name,weight_norm)
sparsefeat : a instance of
SparseFeatmaxlen : maximum length of this feature for all samples
combiner : pooling method,can be
sum,meanormaxlength_name : feature length name,if
None, value 0 in feature is for padding.weight_name : default
None. If not None, the sequence feature will be multiplyed by the feature whose name isweight_name.weight_norm : default
True. Whether normalize the weight score or not.
Models¶
DSSM (Deep Structured Semantic Model)¶

Deep Structured Semantic Models for Web Search using Clickthrough Data
SDM (Sequential Deep Matching Model)¶

SDM: Sequential Deep Matching Model for Online Large-scale Recommender System
MIND (Multi-Interest Network with Dynamic routing)¶

Multi-interest network with dynamic routing for recommendation at Tmall
COMIREC (Controllable Multi-Interest Framework for Recommendation)¶


