2 citations · 6 across the 12 of their papers we have counts for
12 papers
Efficient LLM-based Advertising via Model Compression and Parallel Verification
Wenxin Dong, Chang Gao, Guanghui Yu +9
Large language models (LLMs) have shown remarkable potential in advertising scenarios such as ad creative generation and targeted advertising. However, deploying LLMs in real-time…
FedAds: A Benchmark for Privacy-Preserving CVR Estimation with Vertical Federated Learning
Penghui Wei, Hongjian Dou, Shaoguo Liu +4
Conversion rate (CVR) estimation aims to predict the probability of conversion event after a user has clicked an ad. Typically, online publisher has user browsing interests and cli…
Hybrid Contrastive Constraints for Multi-Scenario Ad Ranking
Shanlei Mu, Penghui Wei, Wayne Xin Zhao +3
Multi-scenario ad ranking aims at leveraging the data from multiple domains or channels for training a unified ranking model to improve the performance at each individual scenario.…
RLTP: Reinforcement Learning to Pace for Delayed Impression Modeling in Preloaded Ads
Penghui Wei, Yongqiang Chen, Shaoguo Liu +2
To increase brand awareness, many advertisers conclude contracts with advertising platforms to purchase traffic and then deliver advertisements to target audiences. In a whole deli…
Correlative Preference Transfer with Hierarchical Hypergraph Network for Multi-Domain Recommendation
Zixuan Xu, Penghui Wei, Shaoguo Liu +3
Advanced recommender systems usually involve multiple domains (such as scenarios or categories) for various marketing strategies, and users interact with them to satisfy diverse de…
AdaSparse: Learning Adaptively Sparse Structures for Multi-Domain Click-Through Rate Prediction
Xuanhua Yang, Xiaoyu Peng, Penghui Wei +3
Click-through rate (CTR) prediction is a fundamental technique in recommendation and advertising systems. Recent studies have proved that learning a unified model to serve multiple…
Towards Personalized Bundle Creative Generation with Contrastive Non-Autoregressive Decoding
Penghui Wei, Shaoguo Liu, Xuanhua Yang +2
Current bundle generation studies focus on generating a combination of items to improve user experience. In real-world applications, there is also a great need to produce bundle cr…
CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning
Penghui Wei, Xuanhua Yang, Shaoguo Liu +2
This paper focuses on automatically generating the text of an ad, and the goal is that the generated text can capture user interest for achieving higher click-through rate (CTR). W…
Posterior Probability Matters: Doubly-Adaptive Calibration for Neural Predictions in Online Advertising
Penghui Wei, Weimin Zhang, Ruijie Hou +4
Predicting user response probabilities is vital for ad ranking and bidding. We hope that predictive models can produce accurate probabilistic predictions that reflect true likeliho…
UKD: Debiasing Conversion Rate Estimation via Uncertainty-regularized Knowledge Distillation
Zixuan Xu, Penghui Wei, Weimin Zhang +3
In online advertising, conventional post-click conversion rate (CVR) estimation models are trained using clicked samples. However, during online serving the models need to estimate…
A Knowledge Enhanced Learning and Semantic Composition Model for Multi-Claim Fact Checking
Shuai Wang, Penghui Wei, Qingchao Kong +1
To inhibit the spread of rumorous information and its severe consequences, traditional fact checking aims at retrieving relevant evidence to verify the veracity of a given claim. F…
Modeling Conversation Structure and Temporal Dynamics for Jointly Predicting Rumor Stance and Veracity
Penghui Wei, Nan Xu, Wenji Mao
Automatically verifying rumorous information has become an important and challenging task in natural language processing and social media analytics. Previous studies reveal that pe…