Yang Yang

Yang Yang

Auto-generated profile, based on publicly available information

Yang Yang

Huawei Noah's Ark Lab, Shanghai, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 October 2024
Verified
Conference Paper
Open access
YYYang Yang
Yang Yang
BCBo Chen
Bo Chen
CZChenxu Zhu
Chenxu Zhu
MZMenghui Zhu
Menghui Zhu
XDXinyi Dai
Xinyi Dai
RTRuiming Tang
Ruiming Tang
Click-Through Rate (CTR) prediction is a fundamental technique for online advertising recommendation and the complex online competitive auction process also brings many difficulties to CTR optimization. Recent studies have shown that introducing posterior auction information contributes to the performance of CTR prediction. However, existing work doesn’t fully capitalize on the benefits of auction information and overlooks the data bias brought by the auction, leading to biased and suboptimal results. To address these limitations, we propose Auction Information Enhanced Framework (AIE) for CTR prediction in online advertising, which delves into the problem of insufficient utilization of auction signals and first reveals the auction bias. Specifically, AIE introduces two pluggable modules, namely Adaptive Market-price Auxiliary Module (AM2) and Bid Calibration Module (BCM), which work collaboratively to excavate the posterior auction signals better and enhance the performance of CTR prediction. Furthermore, the two proposed modules are lightweight, model-agnostic, and friendly to inference latency. Extensive experiments are conducted on a public dataset and an industrial dataset to demonstrate the effectiveness and compatibility of AIE. Besides, a one-month online A/B test in a large-scale advertising platform shows that AIE improves the base model by 5.76% and 2.44% in terms of eCPM and CTR, respectively.

21 October 2024
Verified
Conference Paper
Open access
HLHuanshuo Liu
Huanshuo Liu
BCBo Chen
Bo Chen
MZMenghui Zhu
Menghui Zhu
JLJianghao Lin
Jianghao Lin
JQJiarui Qin
Jiarui Qin
RTRuiming Tang
Ruiming Tang
Click-through rate (CTR) prediction is crucial for personalized online services. Sample-level retrieval-based models, such as RIM, have demonstrated remarkable performance. However, they face challenges including inference inefficiency and high resource consumption due to the retrieval process, which hinder their practical application in industrial settings. To address this, we propose a universal plug-and-play retrieval-oriented knowledge (ROK) framework that bypasses the real retrieval process. The framework features a knowledge base that preserves and imitates the retrieved & aggregated representations using a decomposition-reconstruction paradigm. Knowledge distillation and contrastive learning optimize the knowledge base, enabling the integration of retrieval-enhanced representations with various CTR models. Experiments on three large-scale datasets demonstrate ROK's exceptional compatibility and performance, with the neural knowledge base serving as an effective surrogate for the retrieval pool. ROK surpasses the teacher model while maintaining superior inference efficiency and demonstrates the feasibility of distilling knowledge from non-parametric methods using a parametric approach. These results highlight ROK's strong potential for real-world applications and its ability to transform retrieval-based methods into practical solutions. Our implementation code is available to support reproducibility1.

8 May 2025
Verified
Conference Paper
Open access
XHXu Huang
Xu Huang
XCXiaolong Chen
Xiaolong Chen
YWYichao Wang
Yichao Wang
WLWeiwen Liu
Weiwen Liu
YYYang Yang
Yang Yang
RTRuiming Tang
Ruiming Tang