Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems

Kang Wang-Cheng
Kang Wang-Cheng
Cheng Derek Zhiyuan
Cheng Derek Zhiyuan
Lin Dong
Lin Dong

WWW '20: The Web Conference 2020 Taipei Taiwan April, 2020, pp. 562-566, 2020.

Cited by: 0|Bibtex|Views63|DOI:https://doi.org/10.1145/3366424.3383416
EI
Other Links: arxiv.org|dl.acm.org|dblp.uni-trier.de|academic.microsoft.com

Abstract:

Recommender system models often represent various sparse features like users, items, and categorical features via embeddings. A standard approach is to map each unique feature value to an embedding vector. The size of the produced embedding table grows linearly with the size of the vocabulary. Therefore, a large vocabulary inevitably lead...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments