.png){kind=icon}
返回
Embedding Compression in Recommender Systems: A Survey
.png){kind=icon}
PRE
AI
DOI：10.1145/3637841.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
To alleviate the problem of information explosion, recommender systems are widely deployed to provide personalized information filtering services. Usually, embedding tables are employed in recommender systems to transform high-dimensional sparse one-hot vectors into dense real-valued embeddings. However, the embedding tables are huge and account for most of the parameters in industrial-scale recommender systems. In order to reduce memory costs and improve efficiency, various approaches are proposed to compress the embedding tables. In this survey, we provide a comprehensive review of embedding compression approaches in recommender systems. We first introduce deep learning recommendation models and the basic concept of embedding compression in recommender systems. Subsequently, we systematically organize existing approaches into three categories: low precision, mixed dimension, and weight sharing. Lastly, we summarize the survey with some general suggestions and provide future prospects for this field.
Keyword:
recommender systems
embedding tables
model compression
survey
期刊
IF:
28
论文数:
2.5K
被引数:
3.5W
机构
引用论文
.png){kind=icon}
分享收藏Fastigial Stimulation Increases Ischemic Blood Flow and Reduces Brain Damage after Focal Ischemia
OAAI
OAAI分享收藏分享收藏GABAA receptor currents recorded from Müller glial cells of the baboon (Papio cynocephalus) retina
PREAI
分享收藏
查看更多内容