P
Peng Kang
Researcher at Northwestern University
Publications - 5
Citations - 268
Peng Kang is an academic researcher from Northwestern University. The author has contributed to research in topics: Recommender system & Autoencoder. The author has an hindex of 3, co-authored 5 publications receiving 144 citations. Previous affiliations of Peng Kang include McGill University.
Papers
More filters
Proceedings ArticleDOI
Hierarchical Gating Networks for Sequential Recommendation
Chen Ma,Peng Kang,Xue Liu +2 more
TL;DR: Wang et al. as discussed by the authors proposed a hierarchical gating network (HGN) to capture both the long-term and short-term user interests in sequential recommender systems.
Proceedings ArticleDOI
Gated Attentive-Autoencoder for Content-Aware Recommendation
TL;DR: A gated attentive-autoencoder model, which is capable of learning fused hidden representations of items' contents and binary ratings, through a neural gating structure, and which exploits neighboring relations between items to help infer users' preferences.
Posted Content
Gated Attentive-Autoencoder for Content-Aware Recommendation
TL;DR: Zhang et al. as discussed by the authors proposed a gated attentive-autoencoder (GATE) model, which is capable of learning fused hidden representations of items' contents and binary ratings, through a neural gating structure.
Posted Content
Hierarchical Gating Networks for Sequential Recommendation
Chen Ma,Peng Kang,Xue Liu +2 more
TL;DR: A hierarchical gating network (HGN) integrated with the Bayesian Personalized Ranking (BPR) to capture both the long-term and short-term user interests is proposed, and the experimental results demonstrate the effectiveness of the model on Top-N sequential recommendation.
Proceedings ArticleDOI
ATM: Attentional Text Matting
TL;DR: Zhang et al. as discussed by the authors proposed a two-stage attentional text matting pipeline to solve the problem of image matting, which employs text detection methods to serve as the attention mechanism and matting system to obtain mattes of these text regions.