Search

Your search keyword '"Chen, Wenqiang"' showing total 936 results
Start Over Author "Chen, Wenqiang"
936 results on '"Chen, Wenqiang"'

21. FLEN: Leveraging Field for Scalable CTR Prediction

Author

Chen, Wenqiang, Zhan, Lizhang, Ci, Yuanlong, Yang, Minghua, Lin, Chen, and Liu, Dugang

Subjects
Computer Science - Information Retrieval, Computer Science - Machine Learning
Abstract

Click-Through Rate (CTR) prediction has been an indispensable component for many industrial applications, such as recommendation systems and online advertising. CTR prediction systems are usually based on multi-field categorical features, i.e., every feature is categorical and belongs to one and only one field. Modeling feature conjunctions is crucial for CTR prediction accuracy. However, it requires a massive number of parameters to explicitly model all feature conjunctions, which is not scalable for real-world production systems. In this paper, we describe a novel Field-Leveraged Embedding Network (FLEN) which has been deployed in the commercial recommender system in Meitu and serves the main traffic. FLEN devises a field-wise bi-interaction pooling technique. By suitably exploiting field information, the field-wise bi-interaction pooling captures both inter-field and intra-field feature conjunctions with a small number of model parameters and an acceptable time complexity for industrial applications. We show that a variety of state-of-the-art CTR models can be expressed under this technique. Furthermore, we develop Dicefactor: a dropout technique to prevent independent latent features from co-adapting. Extensive experiments, including offline evaluations and online A/B testing on real production systems, demonstrate the effectiveness and efficiency of FLEN against the state-of-the-arts. Notably, FLEN has obtained 5.19% improvement on CTR with 1/6 of memory usage and computation time, compared to last version (i.e. NFM)., Comment: KDD'20 DLP workshop, 9 pages

Published
2019

28. Multi-branch Cable Harness Layout Optimization Based on Pattern Search Improved Particle Swarm Optimization Algorithm

Author

Zhang, Dan, Cai, Chaoli, Zhou, Chen, Chen, Wenqiang, Ceccarelli, Marco, Series Editor, Agrawal, Sunil K., Advisory Editor, Corves, Burkhard, Advisory Editor, Glazunov, Victor, Advisory Editor, Hernández, Alfonso, Advisory Editor, Huang, Tian, Advisory Editor, Jauregui Correa, Juan Carlos, Advisory Editor, Takeda, Yukio, Advisory Editor, and Tan, Jianrong, editor

Published
2022
Full Text
View/download PDF

38. Calculation of ground potential and magnetic bias current of power grid near the grounding electrode of Chen’an Village

Author

HU Jingen, CHEN Wenqiang, WEI Huabing, ZHU Guichi, and YAO Hui

Subjects
uhvdc, grounding electrode, transformer magnetic bias, magnetic bias treatment, Electrical engineering. Electronics. Nuclear engineering, TK1-9971
Abstract

In view of the high operating current of ±800 kV UHVDC， the influence of earth current at the grounding electrode on the magnetic bias of transformers and the treatment has become a research topic. Given the construction of the ±800kV Baihetan-Zhebei DC transmission project， historical magnetotelluric detection data was used to establish a three-dimensional grounding resistivity model near the grounding electrode of Chen’an Village in northern Zhejiang province. The calculation of station ground potential of power grid near the grounding electrode was completed according to the working condition of 5， 000 A grounding current， and the ground potential calculation results of 124 power plants and substations in the north Zhejiang power grid were obtained. Moreover， a power grid bias current model was established， the bias current was calculated， and a bias treatment plan was proposed. The research results show that compared with the influence of the Jinsi earth pole of the ±800 kV Xiluodu-West Zhejiang DC project， the influence of the current of the grounding electrode in Chen’an Village is less because the transmission lines of North Zhejiang power grid are relatively denser and the lines are short.

Published
2022
Full Text
View/download PDF

45. Selection of Reference Genes in Siraitia siamensis and Expression Patterns of Genes Involved in Mogrosides Biosynthesis.

Author

Chen, Wenqiang, Lin, Xiaodong, Wang, Yan, Mu, Detian, Mo, Changming, Huang, Huaxue, Zhao, Huan, Luo, Zuliang, Liu, Dai, Wilson, Iain W., Qiu, Deyou, and Tang, Qi

Subjects
GENE expression, GENE expression profiling, HERBAL medicine, BIOSYNTHESIS, CELL cycle proteins
Abstract

Siraitia siamensis is a traditional Chinese medicinal herb. In this study, using S. siamensis cultivated in vitro, twelve candidate reference genes under various treatments were analyzed for their expression stability by using algorithms such as GeNorm, NormFinder, BestKeeper, Delta CT, and RefFinder. The selected reference genes were then used to characterize the gene expression of cucurbitadienol synthase, which is a rate-limiting enzyme for mogroside biosynthesis. The results showed that CDC6 and NCBP2 expression was the most stable across all treatments and are the best reference genes under the tested conditions. Utilizing the validated reference genes, we analyzed the expression profiles of genes related to the synthesis pathway of mogroside in S. siamensis in response to a range of abiotic stresses. The findings of this study provide clear standards for gene expression normalization in Siraitia plants and exploring the rationale behind differential gene expression related to mogroside synthesis pathways. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results