Paper Info
Title
Dynamic Hypergraph Convolutional Network
Abstract
Hypergraph Convolutional Network (HCN) has become a proper choice for capturing high-order relationships. Existing HCN methods are tailored for static hypergraphs, which are unsuitable for the dynamic evolution in real-world scenarios. In this paper, we explore a dynamic HCN based on the attention mechanism (DyHCN) for time series prediction. It not only effectively exploits the spatial and temporal relationships in the dynamic hypergraph, but also continuously aggregates the temporal evolution cues of time-varying hypergraphs with the global and local embeddings. Specifically, these merits can be attributed to 1) dynamic hypergraph construction (DHC), which captures the feature of historical context content and provides a guideline for dynamic hypergraph construction; 2) spatiotemporal hypergraph convolution module (STHC), responsible for extracting the spatial and temporal relationships among nodes and hyperedges, and 3) collaborative prediction module (CP), for the overall time-varying hypergraphs embedding aggregation. Such modules endeavor to well learn feature embedding from nodes, hyperedges, and hypergraphs, which produces informative representations for downstream tasks. Experiments on three datasets including Tiingo, Stocktwits, and NYC-Taxi demonstrate that the proposed DyHCN achieves sound performance over existing cousins, and both STHC and CP modules play a key role in modeling the dynamic evolution property of hypergraphs.
Year
DOI
Venue
2022
10.1109/ICDE53745.2022.00167
2022 IEEE 38TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2022)
Keywords
DocType
ISSN
dynamic hypergraph, hypergraph convolutional network, attention mechanism, time series prediction
Conference
1084-4627
Citations 
PageRank 
References 
0
0.34
0
Authors
8
Name
Order
Citations
PageRank
Nan Yin100.34
Fuli Feng249533.75
Zhigang Luo301.01
Xiang Zhang400.68
Wenjie Wang500.34
Xiao Luo600.34
Chong Chen700.34
Xian-Sheng Hua86566328.17