Yi Zheng

Yi Zheng

Auto-generated profile, based on publicly available information

Yi Zheng

Huawei Cloud, Hangzhou, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 January 2024 in ACM Transactions on the Web
Verified
Journal Article
Open access
PLPengfei Luo
Pengfei Luo
XZXi Zhu
Xi Zhu
Tong XuTong Xu
Tong Xu
YZYi Zheng
Yi Zheng
ECEnhong Chen
Enhong Chen
The prosperity of knowledge graphs, as well as related downstream applications, has raised the urgent need for knowledge graph completion techniques that fully support knowledge graph reasoning tasks, especially under the circumstance of training data scarcity. Although large efforts have been made on solving this challenge via few-shot learning tools, they mainly focus on simply aggregating entity neighbors to represent few-shot references, whereas the enhancement from latent semantic correlation within neighbors has been largely ignored. To that end, in this article, we propose a novel few-shot learning solution named SIM, a S emantic I nteraction M atching network that applies a Transformer framework to enhance the entity representation with capturing semantic interaction between entity neighbors. Specifically, we first design an entity-relation fusion module to adaptively encode neighbors with incorporating relation representation. Along this line, Transformer layers are integrated to capture latent correlation within neighbors, as well as the semantic diversification of the support set. Finally, a similarity score is attentively estimated with the attention mechanism. Extensive experiments on two public benchmark datasets demonstrate that our model outperforms a variety of state-of-the-art methods by a significant margin.


28 October 2024
Verified
Conference Paper
Open access
YZYi Zhang
Yi Zhang
ZWZhefeng Wang
Zhefeng Wang
RHRui Hu
Rui Hu
XDXinyu Duan
Xinyu Duan
YZYi Zheng
Yi Zheng
JSJitao Sang
Jitao Sang
Neural networks often tend to rely on bias features that have strong but spurious correlations with the target labels for decision-making, leading to poor performance on data that does not adhere to these correlations. Early debiasing methods typically construct an unbiased optimization objective based on the labels of bias features. Recent work assumes that bias label is unavailable and usually trains two models: a biased model to deliberately learn bias features for exposing data bias, and a target model to eliminate bias captured by the bias model. In this paper, we first reveal that previous biased models fit target labels, which resulted in failing to expose data bias. To tackle this issue, we propose poisoner, which utilizes data poisoning to embed the biases learned by biased models into the poisoned training data, thereby encouraging the models to learn more biases. Specifically, we couple data poisoning and model training to continuously prompt the biased model to learn more bias. By utilizing the biased model, we can identify samples in the data that contradict these biased correlations. Subsequently, we amplify the influence of these samples in the training of the target model to prevent the model from learning such biased correlations. Experiments show the superior debiasing performance of our method.

1 October 2014
Verified
Conference Paper
Closed access
DYDandan Yin
Dandan Yin
SZSihai Zhang
Sihai Zhang
WZWuYang Zhou
WuYang Zhou
YZYi Zheng
Yi Zheng
Time-correlation of GSM telephone traffic is important for wireless network performance, but lack of in-depth investigation, especially in large-scale networks. In this paper, we investigate this topic using the data of call detail records (CDR) collected in June 2013 from thousands of GSM base stations. Based on results obtained by the Modified Allan Variance (MAVAR), we confirm the long-range dependency for all base stations, which is consistent with existing results. But through comprehensive chi-square test we believe that the call arrivals can NOT always be modeled as Poisson distribution in short-term in most cases, which disagree with previous conclusions. Our work may be beneficial to energy saving, realistic traffic modelling and performance evaluation of cellular networks.

11 June 2026 in Expert Systems with Applications
Verified
Journal Article
Closed access
YJYang Ji
Yang Ji
YSYing Sun
Ying Sun
JLJin Li
Jin Li
ZWZhigaoyuan Wang
Zhigaoyuan Wang
PLPing Li
Ping Li
YZYi Zheng
Yi Zheng