no code implementations • 28 Jul 2024 • Xiang-Rong Sheng, Feifan Yang, Litong Gong, Biao Wang, Zhangming Chan, Yujing Zhang, Yueyao Cheng, Yong-Nan Zhu, Tiezheng Ge, Han Zhu, Yuning Jiang, Jian Xu, Bo Zheng
Despite the recognized potential of multimodal data to improve model accuracy, many large-scale industrial recommendation systems, including Taobao display advertising system, predominantly depend on sparse ID features in their models.
no code implementations • 14 Dec 2023 • Xiaoqiang Gui, Yueyao Cheng, Xiang-Rong Sheng, Yunfeng Zhao, Guoxian Yu, Shuguang Han, Yuning Jiang, Jian Xu, Bo Zheng
A typical practice is privileged features distillation (PFD): train a teacher model using all features (including privileged ones) and then distill the knowledge from the teacher model using a student model (excluding the privileged features), which is then employed for online serving.
no code implementations • 9 Aug 2023 • Yunfeng Zhao, Xu Yan, Xiaoqiang Gui, Shuguang Han, Xiang-Rong Sheng, Guoxian Yu, Jufeng Chen, Zhao Xu, Bo Zheng
Furthermore, there is delayed feedback in both conversion and refund events and they are sequentially dependent, named cascade delayed feedback (CDF), which significantly harms data freshness for model training.
no code implementations • 6 Jun 2023 • Zhishan Zhao, Jingyue Gao, Yu Zhang, Shuguang Han, Siyuan Lou, Xiang-Rong Sheng, Zhe Wang, Han Zhu, Yuning Jiang, Jian Xu, Bo Zheng
In this architecture, the pre-ranking model is expected to be a lightweight approximation of the ranking model, which handles more candidates with strict latency requirements.
1 code implementation • 22 May 2023 • Zhangming Chan, Yu Zhang, Shuguang Han, Yong Bai, Xiang-Rong Sheng, Siyuan Lou, Jiacen Hu, Baolin Liu, Yuning Jiang, Jian Xu, Bo Zheng
However, we observe that a well-trained CVR prediction model often performs sub-optimally during sales promotions.
1 code implementation • 4 Sep 2022 • Zhao-Yu Zhang, Xiang-Rong Sheng, Yujing Zhang, Biye Jiang, Shuguang Han, Hongbo Deng, Bo Zheng
However, far less attention has been paid to the overfitting problem of models in recommendation systems, which, on the contrary, is recognized as a critical issue for deep neural networks.
1 code implementation • 12 Aug 2022 • Xiang-Rong Sheng, Jingyue Gao, Yueyao Cheng, Siran Yang, Shuguang Han, Hongbo Deng, Yuning Jiang, Jian Xu, Bo Zheng
It can be attributed to the calibration ability of the pointwise loss since the prediction can be viewed as the click probability.
1 code implementation • 29 Apr 2021 • Siyu Gu, Xiang-Rong Sheng, Ying Fan, Guorui Zhou, Xiaoqiang Zhu
If conversion happens outside the waiting window, this sample will be duplicated and ingested into the training pipeline with a positive label.
no code implementations • 27 Jan 2021 • Xiang-Rong Sheng, Liqin Zhao, Guorui Zhou, Xinyao Ding, Binding Dai, Qiang Luo, Siran Yang, Jingshan Lv, Chi Zhang, Hongbo Deng, Xiaoqiang Zhu
Concretely, STAR has the star topology, which consists of the shared centered parameters and domain-specific parameters.
no code implementations • 11 Nov 2020 • Weijie Bian, Kailun Wu, Lejian Ren, Qi Pi, Yujing Zhang, Can Xiao, Xiang-Rong Sheng, Yong-Nan Zhu, Zhangming Chan, Na Mou, Xinchen Luo, Shiming Xiang, Guorui Zhou, Xiaoqiang Zhu, Hongbo Deng
For example, a simple attempt to learn the combination of feature A and feature B <A, B> as the explicit cartesian product representation of new features can outperform previous implicit feature interaction models including factorization machine (FM)-based models and their variations.