59 citations · 76 across the 8 of their papers we have counts for
8 papers
Multivariate Time Series Classification with Hierarchical Variational Graph Pooling
Ziheng Duan, Haoyan Xu, Yueyang Wang +5
With the advancement of sensing technology, multivariate time series classification (MTSC) has recently received considerable attention. Existing deep learning-based MTSC technique…
MTHetGNN: A Heterogeneous Graph Embedding Framework for Multivariate Time Series Forecasting
Yueyang Wang, Ziheng Duan, Yida Huang +3
Multivariate time series forecasting, which analyzes historical time series to predict future trends, can effectively help decision-making. Complex relations among variables in MTS…
Parallel Extraction of Long-term Trends and Short-term Fluctuation Framework for Multivariate Time Series Forecasting
Yifu Zhou, Ziheng Duan, Haoyan Xu +4
Multivariate time series forecasting is widely used in various fields. Reasonable prediction results can assist people in planning and decision-making, generate benefits and avoid…
TIMME: Twitter Ideology-detection via Multi-task Multi-relational Embedding
Zhiping Xiao, Weiping Song, Haoyan Xu +2
We aim at solving the problem of predicting people's ideology, or political tendency. We estimate it by using Twitter data, and formalize it as a classification problem. Ideology-d…
Graph Partitioning and Graph Neural Network based Hierarchical Graph Matching for Graph Similarity Computation
Haoyan Xu, Ziheng Duan, Jie Feng +4
Graph similarity computation aims to predict a similarity score between one pair of graphs to facilitate downstream applications, such as finding the most similar chemical compound…
CoSimGNN: Towards Large-scale Graph Similarity Computation
Haoyan Xu, Runjian Chen, Yueyang Wang +2
The ability to compute similarity scores between graphs based on metrics such as Graph Edit Distance (GED) is important in many real-world applications. Computing exact GED values…
Multivariate Time Series Forecasting with Transfer Entropy Graph
Ziheng Duan, Haoyan Xu, Yida Huang +2
Multivariate time series (MTS) forecasting is an essential problem in many fields. Accurate forecasting results can effectively help decision-making. To date, many MTS forecasting…
Improved object recognition using neural networks trained to mimic the brain's statistical properties
Callie Federer, Haoyan Xu, Alona Fyshe +1
The current state-of-the-art object recognition algorithms, deep convolutional neural networks (DCNNs), are inspired by the architecture of the mammalian visual system, and are cap…