no code implementations • 22 Oct 2024 • Chang Meng, Chenhao Zhai, Xueliang Wang, Shuchang Liu, Xiaoqiang Feng, Lantao Hu, Xiu Li, Han Li, Kun Gai
These two modules work together to dynamically identify and targeting specific user groups and applying treatments effectively.
1 code implementation • 29 Jan 2024 • Xiaobei Wang, Shuchang Liu, Xueliang Wang, Qingpeng Cai, Lantao Hu, Han Li, Peng Jiang, Kun Gai, Guangming Xie
Furthermore, we show that a reward-based future decomposition strategy can better express the item-wise future impact and improve the recommendation accuracy in the long term.
no code implementations • 3 Feb 2023 • Qingpeng Cai, Shuchang Liu, Xueliang Wang, Tianyou Zuo, Wentao Xie, Bin Yang, Dong Zheng, Peng Jiang, Kun Gai
In this paper, we choose reinforcement learning methods to optimize the retention as they are designed to maximize the long-term performance.
1 code implementation • 3 Feb 2023 • Qingpeng Cai, Zhenghai Xue, Chi Zhang, Wanqi Xue, Shuchang Liu, Ruohan Zhan, Xueliang Wang, Tianyou Zuo, Wentao Xie, Dong Zheng, Peng Jiang, Kun Gai
One the one hand, the platforms aims at optimizing the users' cumulative watch time (main goal) in long term, which can be effectively optimized by Reinforcement Learning.
no code implementations • 16 Jun 2022 • Xueliang Wang, Jiajun Chen, Feng Wu, Jie Wang
By enforcing the entities' embeddings close to their associated prototypes' embeddings, our approach can effectively encourage the global semantic similarities of entities -- that can be far away in the KG -- connected by the same relation.
no code implementations • 16 Jun 2022 • Xueliang Wang, Jianyu Cai, Shuiwang Ji, Houqiang Li, Feng Wu, Jie Wang
A major novelty of SALA is the task-adaptive metric, which can learn the metric adaptively for different tasks in an end-to-end fashion.
no code implementations • 13 Jun 2022 • Ruohan Zhan, Changhua Pei, Qiang Su, Jianfeng Wen, Xueliang Wang, Guanyu Mu, Dong Zheng, Peng Jiang
We employ a causal graph illuminating that duration is a confounding factor that concurrently affects video exposure and watch-time prediction -- the first effect on video causes the bias issue and should be eliminated, while the second effect on watch time originates from video intrinsic characteristics and should be preserved.