no code implementations • 5 Dec 2024 • Yuhao Wang, Junwei Pan, Xiangyu Zhao, Pengyue Jia, Wanyu Wang, YuAn Wang, Yue Liu, Dapeng Liu, Jie Jiang
Sequential recommendation (SR) aims to model the sequential dependencies in users' historical interactions to better capture their evolving interests.
no code implementations • 19 Nov 2024 • Yu Kang, Junwei Pan, Jipeng Jin, Shudong Huang, Xiaofeng Gao, Lei Xiao
Modeling feature interactions plays a crucial role in accurately predicting click-through rates (CTR) in advertising systems.
no code implementations • 12 Oct 2024 • Taolin Zhang, Junwei Pan, Jinpeng Wang, Yaohua Zha, Tao Dai, Bin Chen, Ruisheng Luo, Xiaoxiang Deng, YuAn Wang, Ming Yue, Jie Jiang, Shu-Tao Xia
With recent advances in large language models (LLMs), there has been emerging numbers of research in developing Semantic IDs based on LLMs to enhance the performance of recommendation systems.
no code implementations • 3 Oct 2024 • Ningya Feng, Junwei Pan, Jialong Wu, Baixu Chen, Ximei Wang, Qian Li, Xian Hu, Jie Jiang, Mingsheng Long
In this work, we identify and characterize, for the first time, a neglected deficiency in existing long-sequence recommendation models: a single set of embeddings struggles with learning both attention and representation, leading to interference between these two processes.
no code implementations • 21 May 2024 • Zhutian Lin, Junwei Pan, Haibin Yu, Xi Xiao, Ximei Wang, Zhixiang Feng, Shifeng Wen, Shudong Huang, Dapeng Liu, Lei Xiao
However, this leads to a challenging dilemma in MDL.
no code implementations • 17 Apr 2024 • Hengyu Zhang, Junwei Pan, Dapeng Liu, Jie Jiang, Xiu Li
These patterns harbor substantial potential to significantly enhance CTR prediction performance.
1 code implementation • 21 Mar 2024 • Zhutian Lin, Junwei Pan, Shangyu Zhang, Ximei Wang, Xi Xiao, Shudong Huang, Lei Xiao, Jie Jiang
We introduce a novel perspective on the effectiveness of the auxiliary ranking loss in CTR prediction: it generates larger gradients on negative samples, thereby mitigating the optimization difficulties when using the BCE loss only and resulting in improved classification ability.
1 code implementation • 22 Feb 2024 • Junwei Pan, Wei Xue, Ximei Wang, Haibin Yu, Xun Liu, Shijie Quan, Xueming Qiu, Dapeng Liu, Lei Xiao, Jie Jiang
We present Tencent's ads recommendation system and examine the challenges and practices of learning appropriate recommendation representations.
2 code implementations • 6 Oct 2023 • Xingzhuo Guo, Junwei Pan, Ximei Wang, Baixu Chen, Jie Jiang, Mingsheng Long
On the one hand, interacting with collapsed embeddings restricts embedding learning and exacerbates the collapse issue.
no code implementations • 19 Sep 2023 • Ximei Wang, Junwei Pan, Xingzhuo Guo, Dapeng Liu, Jie Jiang
Multi-domain learning (MDL) aims to train a model with minimal average risk across multiple overlapping but non-identical domains.
2 code implementations • 16 Aug 2023 • Liangcai Su, Junwei Pan, Ximei Wang, Xi Xiao, Shijie Quan, Xihua Chen, Jie Jiang
Surprisingly, negative transfer still occurs in existing MTL methods on samples that receive comparable feedback across tasks.
2 code implementations • 15 Aug 2023 • Haolin Zhou, Junwei Pan, Xinyi Zhou, Xihua Chen, Jie Jiang, Xiaofeng Gao, Guihai Chen
To fill this gap, we propose a Temporal Interest Network (TIN) to capture the semantic-temporal correlation simultaneously between behaviors and the target.
1 code implementation • NeurIPS 2023 • Junguang Jiang, Baixu Chen, Junwei Pan, Ximei Wang, Liu Dapeng, Jie Jiang, Mingsheng Long
Auxiliary-Task Learning (ATL) aims to improve the performance of the target task by leveraging the knowledge obtained from related tasks.
no code implementations • 28 Nov 2022 • Enneng Yang, Junwei Pan, Ximei Wang, Haibin Yu, Li Shen, Xihua Chen, Lei Xiao, Jie Jiang, Guibing Guo
In this paper, we propose to measure the task dominance degree of a parameter by the total updates of each task on this parameter.
no code implementations • 27 Oct 2022 • Zuowu Zheng, Xiaofeng Gao, Junwei Pan, Qi Luo, Guihai Chen, Dapeng Liu, Jie Jiang
In this paper, we propose a novel model named AutoAttention, which includes all item/user/context side fields as the query, and assigns a learnable weight for each field pair between behavior fields and query fields.
no code implementations • 25 Apr 2022 • Chenxiao Yang, Qitian Wu, Jipeng Jin, Xiaofeng Gao, Junwei Pan, Guihai Chen
To circumvent false negatives, we develop a principled approach to improve the reliability of negative instances and prove that the objective is an unbiased estimation of sampling from the true negative distribution.
no code implementations • 11 Mar 2022 • Di wu, Cheng Chen, Xiujun Chen, Junwei Pan, Xun Yang, Qing Tan, Jian Xu, Kuang-Chih Lee
In order to address the unstable traffic pattern challenge and achieve the optimal overall outcome, we propose a multi-agent reinforcement learning method to adjust the bids from each guaranteed contract, which is simple, converging efficiently and scalable.
no code implementations • 20 Feb 2022 • Chenxiao Yang, Junwei Pan, Xiaofeng Gao, Tingyu Jiang, Dapeng Liu, Guihai Chen
Multi-task learning (MTL) has been widely used in recommender systems, wherein predicting each type of user feedback on items (e. g, click, purchase) are treated as individual tasks and jointly trained with a unified model.
1 code implementation • 13 Aug 2021 • Haoming Li, Feiyang Pan, Xiang Ao, Zhao Yang, Min Lu, Junwei Pan, Dapeng Liu, Lei Xiao, Qing He
The delayed feedback problem is one of the imperative challenges in online advertising, which is caused by the highly diversified feedback delay of a conversion varying from a few minutes to several days.
no code implementations • 12 Jul 2021 • Tian Zhou, Hao He, Shengjun Pan, Niklas Karlsson, Bharatbhushan Shetty, Brendan Kitts, Djordje Gligorijevic, San Gultekin, Tingyu Mao, Junwei Pan, Jianlong Zhang, Aaron Flores
Since 2019, most ad exchanges and sell-side platforms (SSPs), in the online advertising industry, shifted from second to first price auctions.
2 code implementations • 20 Feb 2021 • Yang Sun, Junwei Pan, Alex Zhang, Aaron Flores
The FmFM model's performance is also comparable to DNN models which require much more FLOPs in runtime.
no code implementations • 5 Dec 2020 • Zhilin Zhang, Xiangyu Liu, Zhenzhe Zheng, Chenrui Zhang, Miao Xu, Junwei Pan, Chuan Yu, Fan Wu, Jian Xu, Kun Gai
In e-commerce advertising, the ad platform usually relies on auction mechanisms to optimize different performance metrics, such as user experience, advertiser utility, and platform revenue.
no code implementations • 19 Sep 2020 • Shengjun Pan, Brendan Kitts, Tian Zhou, Hao He, Bharatbhushan Shetty, Aaron Flores, Djordje Gligorijevic, Junwei Pan, Tingyu Mao, San Gultekin, Jianlong Zhang
We found that bid shading, in general, can deliver significant value to advertisers, reducing price per impression to about 55% of the unshaded cost.
no code implementations • 2 Sep 2020 • Djordje Gligorijevic, Tian Zhou, Bharatbhushan Shetty, Brendan Kitts, Shengjun Pan, Junwei Pan, Aaron Flores
Online auctions play a central role in online advertising, and are one of the main reasons for the industry's scalability and growth.
2 code implementations • 17 Feb 2020 • Wei Deng, Junwei Pan, Tian Zhou, Deguang Kong, Aaron Flores, Guang Lin
To address the issue of significantly increased serving delay and high memory usage for ad serving in production, this paper presents \emph{DeepLight}: a framework to accelerate the CTR predictions in three aspects: 1) accelerate the model inference via explicitly searching informative feature interactions in the shallow component; 2) prune redundant layers and parameters at intra-layer and inter-layer level in the DNN component; 3) promote the sparsity of the embedding layer to preserve the most discriminant signals.
Ranked #8 on
Click-Through Rate Prediction
on Avazu
no code implementations • 17 Aug 2019 • Yizhi Mao, Miao Chen, Abhinav Wagle, Junwei Pan, Michael Natkovich, Don Matheson
At Yahoo Front Page, headline testing is carried out using a test-rollout strategy: we first allocate equal proportion of the traffic to each headline variation for a defined testing period, and then shift all future traffic to the best-performing variation.
no code implementations • 24 Jul 2019 • Junwei Pan, Yizhi Mao, Alfonso Lobos Ruiz, Yu Sun, Aaron Flores
Conversion prediction plays an important role in online advertising since Cost-Per-Action (CPA) has become one of the primary campaign performance objectives in the industry.
5 code implementations • 9 Jun 2018 • Junwei Pan, Jian Xu, Alfonso Lobos Ruiz, Wenliang Zhao, Shengjun Pan, Yu Sun, Quan Lu
The data involved in CTR prediction are typically multi-field categorical data, i. e., every feature is categorical and belongs to one and only one field.