GUIM -- General User and Item Embedding with Mixture of Representation in E-commerce

no code implementations • 2 Jul 2022 • Chao Yang, Ru He, Fangquan Lin, Suoyuan Song, Jingqiao Zhang, Cheng Yang

Our goal is to build general representation (embedding) for each user and each product item across Alibaba's businesses, including Taobao and Tmall which are among the world's biggest e-commerce websites.

Contrastive Learning Marketing

SAS: Self-Augmentation Strategy for Language Model Pre-training

1 code implementation • 14 Jun 2021 • Yifei Xu, Jingqiao Zhang, Ru He, Liangzhu Ge, Chao Yang, Cheng Yang, Ying Nian Wu

In this paper, we propose a self-augmentation strategy (SAS) where a single network is utilized for both regular pre-training and contextualized data augmentation for the training in later epochs.

Data Augmentation Language Modelling +2

Progressively Stacking 2.0: A Multi-stage Layerwise Training Method for BERT Training Speedup

no code implementations • 27 Nov 2020 • Cheng Yang, Shengnan Wang, Chao Yang, Yuechuan Li, Ru He, Jingqiao Zhang

In BERT training, the backward computation is much more time-consuming than the forward computation, especially in the distributed training setting in which the backward computation time further includes the communication time for gradient synchronization.

Structure Learning in Bayesian Networks of Moderate Size by Efficient Sampling

no code implementations • 19 Jan 2015 • Ru He, Jin Tian, Huaiqing Wu

We study the Bayesian model averaging approach to learning Bayesian network structures (DAGs) from data.