no code implementations • 16 Oct 2023 • Yunli Wang, Zhiqiang Wang, Jian Yang, Shiyang Wen, Dongying Kong, Han Li, Kun Gai
Concretely, we employ multi-task learning to adaptively combine the optimization of relaxed and full targets, which refers to metrics Recall@m@k and OPA respectively.
no code implementations • 31 May 2023 • Zhaocheng Liu, Zhongxiang Fan, Jian Liang, Dongying Kong, Han Li
However, it is still unknown whether a multi-epoch training paradigm could achieve better results, as the best performance is usually achieved by one-epoch training.
no code implementations • 14 Jul 2022 • Zhaocheng Liu, Yingtao Luo, Di Zeng, Qiang Liu, Daqing Chang, Dongying Kong, Zhi Chen
Modeling users' dynamic preferences from historical behaviors lies at the core of modern recommender systems.
1 code implementation • 1 Jun 2022 • Yi Guo, Zhaocheng Liu, Jianchao Tan, Chao Liao, Sen yang, Lei Yuan, Dongying Kong, Zhi Chen, Ji Liu
When training is finished, some gates are exact zero, while others are around one, which is particularly favored by the practical hot-start training in the industry, due to no damage to the model performance before and after removing the features corresponding to exact-zero gates.
1 code implementation • 10 Nov 2021 • Xiangru Lian, Binhang Yuan, XueFeng Zhu, Yulong Wang, Yongjun He, Honghuan Wu, Lei Sun, Haodong Lyu, Chengjun Liu, Xing Dong, Yiqiao Liao, Mingnan Luo, Congfei Zhang, Jingru Xie, Haonan Li, Lei Chen, Renjie Huang, Jianying Lin, Chengchun Shu, Xuezhong Qiu, Zhishan Liu, Dongying Kong, Lei Yuan, Hai Yu, Sen yang, Ce Zhang, Ji Liu
Specifically, in order to ensure both the training efficiency and the training accuracy, we design a novel hybrid training algorithm, where the embedding layer and the dense neural network are handled by different synchronization mechanisms; then we build a system called Persia (short for parallel recommendation training system with hybrid acceleration) to support this hybrid training algorithm.
no code implementations • 20 Aug 2021 • Weicong Ding, Hanlin Tang, Jingshuo Feng, Lei Yuan, Sen yang, Guangxu Yang, Jie Zheng, Jing Wang, Qiang Su, Dong Zheng, Xuezhong Qiu, Yongqi Liu, Yuxuan Chen, Yang Liu, Chao Song, Dongying Kong, Kai Ren, Peng Jiang, Qiao Lian, Ji Liu
In this setting with multiple and constrained goals, this paper discovers that a probabilistic strategic parameter regime can achieve better value compared to the standard regime of finding a single deterministic parameter.