Filters








1 Hit in 2.8 sec

GB-CENT

Qian Zhao, Yue Shi, Liangjie Hong
2017 Proceedings of the 26th International Conference on World Wide Web - WWW '17  
Since in real-world applications we usually have both abundant numerical features and categorical features with large cardinality (e.g. geolocations, IDs, tags etc.), we design a new model, called GB-CENT  ...  With two real-world data sets, we demonstrate that GB-CENT can effectively (i.e. fast and accurately) achieve better accuracy than state-of-the-art matrix factorization, decision tree based models and  ...  GB-CENT Model Description We define the following notations to describe our model Gradient Boosted Categorical Embedding and Numerical Trees (GB-CENT). Consider a data set with N instances.  ... 
doi:10.1145/3038912.3052668 dblp:conf/www/ZhaoSH17 fatcat:7khc2ozfofeudaock5bhhscxhi