315 citations · 623 across the 37 of their papers we have counts for
9 papers · 1 filter
Improving Attention Mechanism with Query-Value Interaction
Chuhan Wu, Fangzhao Wu, Tao Qi +1
Attention mechanism has played critical roles in various state-of-the-art NLP models such as Transformer and BERT. It can be formulated as a ternary function that maps the input qu…
PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervision
Chuhan Wu, Fangzhao Wu, Tao Qi +3
User modeling is critical for many personalized web services. Many existing methods model users based on their behaviors and the labeled data of target tasks. However, these method…
DA-Transformer: Distance-aware Transformer
Chuhan Wu, Fangzhao Wu, Yongfeng Huang
Transformer has achieved great success in the NLP field by composing various advanced models like BERT and GPT. However, Transformer and its existing variants may not be optimal in…
FedCTR: Federated Native Ad CTR Prediction with Multi-Platform User Behavior Data
Chuhan Wu, Fangzhao Wu, Tao Di +2
Native ad is a popular type of online advertisement which has similar forms with the native content displayed on websites. Native ad CTR prediction is useful for improving user exp…
Graph-Stega: Semantic Controllable Steganographic Text Generation Guided by Knowledge Graph
Zhongliang Yang, Baitao Gong, Yamin Li +3
Most of the existing text generative steganographic methods are based on coding the conditional probability distribution of each word during the generation process, and then select…
FairRec: Fairness-aware News Recommendation with Decomposed Adversarial Learning
Chuhan Wu, Fangzhao Wu, Xiting Wang +2
News recommendation is important for online news services. Existing news recommendation models are usually learned from users' news click behaviors. Usually the behaviors of users…