no code implementations • 15 May 2023 • Penghui Wei, Hongjian Dou, Shaoguo Liu, Rongjun Tang, Li Liu, Liang Wang, Bo Zheng
We introduce FedAds, the first benchmark for CVR estimation with vFL, to facilitate standardized and systematical evaluations for vFL algorithms.
no code implementations • 6 Feb 2023 • Penghui Wei, Yongqiang Chen, Shaoguo Liu, Liang Wang, Bo Zheng
In a whole delivery period, advertisers usually desire a certain impression count for the ads, and they also expect that the delivery performance is as good as possible (e. g., obtaining high click-through rate).
no code implementations • 6 Feb 2023 • Shanlei Mu, Penghui Wei, Wayne Xin Zhao, Shaoguo Liu, Liang Wang, Bo Zheng
In this paper, we propose a Hybrid Contrastive Constrained approach (HC^2) for multi-scenario ad ranking.
no code implementations • 21 Nov 2022 • Zixuan Xu, Penghui Wei, Shaoguo Liu, Weimin Zhang, Liang Wang, Bo Zheng
Conventional graph neural network based methods usually deal with each domain separately, or train a shared model to serve all domains.
no code implementations • 27 Jun 2022 • Xuanhua Yang, Xiaoyu Peng, Penghui Wei, Shaoguo Liu, Liang Wang, Bo Zheng
Click-through rate (CTR) prediction is a fundamental technique in recommendation and advertising systems.
no code implementations • 30 May 2022 • Penghui Wei, Shaoguo Liu, Xuanhua Yang, Liang Wang, Bo Zheng
Current bundle generation studies focus on generating a combination of items to improve user experience.
no code implementations • NAACL (ACL) 2022 • Penghui Wei, Xuanhua Yang, Shaoguo Liu, Liang Wang, Bo Zheng
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).
no code implementations • 15 May 2022 • Penghui Wei, Weimin Zhang, Ruijie Hou, Jinquan Liu, Shaoguo Liu, Liang Wang, Bo Zheng
Calibration techniques aims to post-process model predictions to posterior probabilities.
no code implementations • 20 Jan 2022 • Zixuan Xu, Penghui Wei, Weimin Zhang, Shaoguo Liu, Liang Wang, Bo Zheng
Then a student model is trained on both clicked and unclicked ads with knowledge distillation, performing uncertainty modeling to alleviate the inherent noise in pseudo-labels.
no code implementations • 27 Apr 2021 • Shuai Wang, Penghui Wei, Jiahao Zhao, Wenji Mao
Our method consists of two modules, KG-based learning enhancement and multi-claim semantic composition.
1 code implementation • ACL 2020 • Penghui Wei, Jiahao Zhao, Wenji Mao
Emotion-cause pair extraction aims to extract all emotion clauses coupled with their cause clauses from a given document.
Ranked #1 on Emotion-Cause Pair Extraction on ECPE-FanSplit
no code implementations • IJCNLP 2019 • Penghui Wei, Nan Xu, Wenji Mao
The bottom component of our framework classifies the stances of tweets in a conversation discussing a rumor via modeling the structural property based on a novel graph convolutional network.