Deep Interest Network for Click-Through Rate Prediction
Citations
802 citations
802 citations
Cites methods from "Deep Interest Network for Click-Thr..."
...Such a SL paradigm for recommendation has been widely deployed in industry [7, 24, 41], and some representative models include factorization machine (FM) [23], NFM (neural FM) [11], Wide&Deep [7], and xDeepFM [18], etc....
[...]
614 citations
550 citations
550 citations
Cites background or methods from "Deep Interest Network for Click-Thr..."
...[45] shows tha traditional RSs can not capture interest diversity and local activation effectively, so they introduce a Deep Interest Network (DIN) to represent users’ diverse interests with an attentive activation mechanism....
[...]
...We can explore the usage of the DIN mechanism [45] to capture the related activation according to the candidate item....
[...]
References
111,197 citations
"Deep Interest Network for Click-Thr..." refers methods in this paper
...Due to the huge size of data, we set the mini-batch size to be 5000 and use Adam[15] as the optimizer....
[...]
40,785 citations
"Deep Interest Network for Click-Thr..." refers background in this paper
... with addition of ne-grained user visited goodidsfeature, model performance falls rapidly after the rst epoch. Many methods have been proposed to reduce overtting, such as L 2 and L 1 regularization [15], and Dropout [16]. However, with sparse and high dimensional data, CTR prediction task faces greater challenge. It is known that internet-scale user behavior data follows the long-tail law, that is, ...
[...]
33,597 citations
30,124 citations
Additional excerpts
...ple, we randomly select 9 categories (dress, sport shoes, bags, etc) and 100 goods of each category as the candidate ads for her. Fig.6 shows the visualization of embedding vectors of goods with t-SNE[17] learned by DIN, in which points with same shape correspond to the same category. We can see that goods with same category almost belong to one cluster, which shows the clustering property of DIN embe...
[...]
27,821 citations