no code implementations • 4 Feb 2024 • Hao Wang, Licheng Pan, Zhichao Chen, Degui Yang, Sen Zhang, Yifei Yang, Xinggao Liu, Haoxuan Li, DaCheng Tao
Time series modeling is uniquely challenged by the presence of autocorrelation in both historical and label sequences.
no code implementations • 31 Jan 2024 • Carsten Monka-Ewe, Lukas Berkelmann, Richard Wolf, Jan Oliver Oelerich, Thorsten Schönfelder, Marco Kühnel, Zhichao Chen, Alin Stanescu, Oliver Kushova, Daniel Siekmann, Bert Jannsen
The ever-increasing need for spectrum for mobile broadband systems has led to the recent allocation of spectral resources for International Mobile Telecommunication (IMT) services in the upper mid band (6. 425 - 7. 125 GHz) at the World Radio Conference (WRC-23) as well as to the creation of an agenda item on identifying future IMT bands in the frequency region 7. 125 - 10. 5 GHz at WRC-27.
no code implementations • 23 Sep 2023 • Zhichao Chen, Leilei Ding, Zhixuan Chu, Yucheng Qi, Jianmin Huang, Hao Wang
Time-Series Forecasting based on Cumulative Data (TSFCD) is a crucial problem in decision-making across various industrial scenarios.
no code implementations • 21 Feb 2023 • Licheng Pan, Hao Wang, Zhichao Chen, Yuxing Huang, Xinggao Liu
We further present a Task-aware Mixture-of-Experts framework for achieving the Pareto optimum (TMoE-P) in multi-variate soft sensor, which consists of a stacked OMoE module and a POR module.
no code implementations • 4 Feb 2023 • Zhichao Chen, Zhiqiang Ge
The basis of Bayesian network is structure learning which learns a directed acyclic graph (DAG) from data.
no code implementations • 20 Oct 2022 • Hao Wang, Zhichao Chen, Jiajun Fan, Yuxin Huang, Weiming Liu, Xinggao Liu
As a basic research problem for building effective recommender systems, post-click conversion rate (CVR) estimation has long been plagued by sample selection bias and data sparsity issues.
1 code implementation • 3 Apr 2022 • Hao Wang, Tai-Wei Chang, Tianqiao Liu, Jianmin Huang, Zhichao Chen, Chao Yu, Ruopeng Li, Wei Chu
In this paper, we theoretically demonstrate that ESMM suffers from the following two problems: (1) Inherent Estimation Bias (IEB), where the estimated CVR of ESMM is inherently higher than the ground truth; (2) Potential Independence Priority (PIP) for CTCVR estimation, where there is a risk that the ESMM overlooks the causality from click to conversion.