Zhiyuan Wang (王志远)

I am currently pursuing the M.S. degree in software engineering at University of Electronic Science and Technology of China (UESTC) supervised by Prof. Fan Zhou.

My recent research interests include time series analysis, graph neural network, and deep generative models.

Email  /  Google Scholar  /  Github

profile photo
Learning Latent Seasonal-Trend Representations for Time Series Forecasting (accept)
Zhiyuan Wang, Xovee Xu, Goce Trajcevski, Weifeng Zhang, Ting Zhong, Fan Zhou
NeurIPS, 2022

Motivated by the success of disentangled variational autoencoder in computer vision and classical time series decomposition, we propose LaST that infers a couple of representations that depict seasonal and trend components of time series. Extensive experiments demonstrates its superiority on the time series forecasting task.

Connecting the Hosts: Street-Level IP Geolocation with Graph Neural Networks (Oral)
Zhiyuan Wang, Wenxuan Zeng, Goce Trajcevski, Kunpeng Zhang, Fan Zhou, Yong Wang, Kai Chen
KDD, 2022

We propose a novel framework named GraphGeo, which first provides a complete processing methodology for street-level IP geolocation with the application of graph neural networks. It incorporates IP hosts knowledge and kinds of neighborhood relationships into the graph to infer spatial topology for high-quality geolocation prediction.

PrEF: Probabilistic Electricity Forecasting via Copula-Augmented State Space Model
Zhiyuan Wang, Xovee Xu, Goce Trajcevski, Kunpeng Zhang, Ting Zhong Fan Zhou,
AAAI, 2022

we propose a novel method named Probabilistic Electricity Forecasting (PrEF) by proposing a non-linear neural state space model (SSM) and incorporating copula-augmented mechanism into that, which can learn uncertainty-dependencies knowledge and understand interactions between various factors from large-scale electricity time series data.

Large-Scale IP Usage Identification via Deep Ensemble Learning (Student Abstract)
Zhiyuan Wang, Fan Zhou, Kunpeng Zhang, Yong Wang,

Less is known about the scenario of an IP address, e.g., dedicated enterprise network or home broadband. In this work, we initiate the first attempt to address a large-scale IP scenario identification problem.

HydroFlow: Towards Probabilistic Electricity Demand Prediction Using Variational Autoregressive Models and Normalizing Flows
Fan Zhou, Zhiyuan Wang, Ting Zhong, Goce Trajcevski, Ashfaq Khokhar
International Journal of Intelligent Systems, 2022

We present HydroFlow, a novel deep generative model for predicting the electricity generation demand of large-scale hydropower stations. It uses a latent stochastic RNN to capture the dependencies in the multivariate time series while considering the uncertainty of variables related to natural and social factors.

© 2022 Zhiyuan Wang | Powered by Jon Barron's design | Updated 2022-02-26