> For the complete documentation index, see [llms.txt](https://codingling.gitbook.io/study/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://codingling.gitbook.io/study/recsys/tui-jian-xi-tong-zhi-zhao-hui-yu-jing-pai/dai-ma/python/recall/deepmatch-master/docs/source/features.md).

# Features

## Feature Columns

### SparseFeat

`SparseFeat` is a namedtuple with signature `SparseFeat(name, vocabulary_size, embedding_dim, use_hash, dtype,embedding_name, group_name)`

* name : feature name
* vocabulary\_size : number of unique feature values for sprase feature or hashing space when `use_hash=True`
* embedding\_dim : embedding dimension
* use\_hash : defualt `False`.If `True` the input will be hashed to space of size `vocabulary_size`.
* dtype : default `float32`.dtype of input tensor.
* embedding\_name : default `None`. If None, the embedding\_name will be same as `name`.
* group\_name : feature group of this feature.

### 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 `SparseFeat`
* maxlen : maximum length of this feature for all samples
* combiner : pooling method,can be `sum`,`mean` or `max`
* length\_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 is `weight_name`.
* weight\_norm : default `True`. Whether normalize the weight score or not.

## Models

### FM (Convolutional Click Prediction Model)

[**FM Model API**](https://github.com/LinglingGreat/StudySum/blob/master/Recsys/推荐系统之召回与精排/代码/python/recall/DeepMatch-master/docs/source/deepmatch.models.fm.html)

[Factorization Machines](https://www.researchgate.net/publication/220766482_Factorization_Machines)

### DSSM (Deep Structured Semantic Model)

[**DSSM Model API**](https://github.com/LinglingGreat/StudySum/blob/master/Recsys/推荐系统之召回与精排/代码/python/recall/DeepMatch-master/docs/source/deepmatch.models.dssm.html)

![DSSM](https://2635718429-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-MF66ktDIaNeQvkO0bzL%2Fuploads%2Fgit-blob-6635828591046a0bf2fe5cc7bffe9269d8816bb0%2Fdssm.jpg?alt=media)

[Deep Structured Semantic Models for Web Search using Clickthrough Data](https://www.microsoft.com/en-us/research/publication/learning-deep-structured-semantic-models-for-web-search-using-clickthrough-data/)

### YoutubeDNN

[**YoutubeDNN Model API**](https://github.com/LinglingGreat/StudySum/blob/master/Recsys/推荐系统之召回与精排/代码/python/recall/DeepMatch-master/docs/source/deepmatch.models.youtubednn.html)

![YoutubeDNN](https://2635718429-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-MF66ktDIaNeQvkO0bzL%2Fuploads%2Fgit-blob-57b68644f46a430a3a51e28ad1be3d74134435cd%2Fyoutubednn.jpg?alt=media)

[Deep Neural Networks for YouTube Recommendations](https://www.researchgate.net/publication/307573656_Deep_Neural_Networks_for_YouTube_Recommendations)

### NCF (Neural Collaborative Filtering)

[**NCF Model API**](https://github.com/LinglingGreat/StudySum/blob/master/Recsys/推荐系统之召回与精排/代码/python/recall/DeepMatch-master/docs/source/deepmatch.models.ncf.html)

![NCF](https://2635718429-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-MF66ktDIaNeQvkO0bzL%2Fuploads%2Fgit-blob-a1984086d09f978a8af3240f21bb14348e52c1fa%2Fncf.jpg?alt=media)

[Neural Collaborative Filtering](https://arxiv.org/abs/1708.05031)

### MIND (Multi-Interest Network with Dynamic routing)

[**MIND Model API**](https://github.com/LinglingGreat/StudySum/blob/master/Recsys/推荐系统之召回与精排/代码/python/recall/DeepMatch-master/docs/source/deepmatch.models.mind.html)

![MIND](https://2635718429-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-MF66ktDIaNeQvkO0bzL%2Fuploads%2Fgit-blob-4dd1388fa132fdb368d60cf4af6120ec0c610d9c%2Fmind.jpg?alt=media)

[Multi-interest network with dynamic routing for recommendation at Tmall](https://arxiv.org/pdf/1904.08030)