Item Embeddings
Item Embeddings is a representation learning technique in which discrete items are mapped into continuous vector spaces such that the geometric relationships among vectors reflect semantic or behavioral similarities and interactions derived from user-item or item-context interactions.
148
Publications
13.1K
Citations
559
Authors
173
Institutions
Publications per year
2017–2026
142
Variants
Item Vector Representations
Parents
148
Improved Recurrent Neural Networks for Session-based Recommendations
Yong Tan, Xinxing Xu, Yong Liu · 2016 · 738 citations
A Simple Convolutional Generative Network for Next Item Recommendation
Fajie Yuan, Alexandros Karatzoglou, Ioannis Arapakis et al. · 2019 · 625 citations · Full text
Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks
2019 · 625 citations · Full text
A Neural Influence Diffusion Model for Social Recommendation
Le Wu, Peijie Sun, Yanjie Fu et al. · 2019 · 573 citations
1–5 of 148
559
10
h-index
10
h-index
7
h-index
7
h-index
6
h-index
1–5 of 559
173
University of Science and Technology of China
Hefei, China
10 h-index
21 publications
1.1K citations

Hefei University of Technology
Hefei, China
10 h-index
34 publications
4.1K citations
National University of Singapore
Singapore, Singapore
8 h-index
17 publications
2.6K citations

Alibaba Group (China)
Hangzhou, China
7 h-index
21 publications
3.2K citations

Zhejiang University
Hangzhou, China
7 h-index
16 publications
705 citations
Tencent (China)
Shenzhen, China
6 h-index
13 publications
1.5K citations
University of Illinois Chicago
Chicago, United States
6 h-index
20 publications
1.2K citations
University of Technology Sydney
Sydney, Australia
5 h-index
12 publications
570 citations
1–8 of 173
Repository · 21 publications · 1K citations
16
h-index
10 publications · 460 citations
10
h-index
Conference · 6 publications · 464 citations
6
h-index
TKDE · 5 publications · 179 citations
5
h-index
Conference · 5 publications · 295 citations
5
h-index
1–5