TY - GEN
T1 - MTT-DynGL
T2 - 23rd IEEE International Conference on Data Mining, ICDM 2023
AU - Shi, Chen
AU - Mao, Yujie
AU - Shen, Yiding
AU - Xiong, Wenli
AU - Liu, Feng
AU - Li, Chenhui
AU - Wang, Changbo
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Dynamic graph learning has received increasing attention in recent years. However, real-world graph data sets are characterized by significant structural complexity, attribute diversity, and temporal variability. Importantly, there are complex and significant influence mechanisms between them. All them pose great challenges to dynamic graph learning (DGL). To address them, we propose a novel dynamic graph learning framework, MTT-DynGL. First, graph attention networks (GAT) is used to efficiently aggregate the topology and multidimensional attribute features on each snapshot. Then, a temporal variation matrix with strength factors is designed to further measure the interaction mechanism between structures and attributes over time. Further, to effectively integrate the above results, a MTT-based dynamic graph learning network is designed. It consists of an MTT integration mechanism and a bidirectional dilated causal convolution network. The former is used to learn temporal variation features in an integrated manner, and the latter is used to improve learning quality and training efficiency. Finally, the effectiveness of our method is verified by multiple experiments.
AB - Dynamic graph learning has received increasing attention in recent years. However, real-world graph data sets are characterized by significant structural complexity, attribute diversity, and temporal variability. Importantly, there are complex and significant influence mechanisms between them. All them pose great challenges to dynamic graph learning (DGL). To address them, we propose a novel dynamic graph learning framework, MTT-DynGL. First, graph attention networks (GAT) is used to efficiently aggregate the topology and multidimensional attribute features on each snapshot. Then, a temporal variation matrix with strength factors is designed to further measure the interaction mechanism between structures and attributes over time. Further, to effectively integrate the above results, a MTT-based dynamic graph learning network is designed. It consists of an MTT integration mechanism and a bidirectional dilated causal convolution network. The former is used to learn temporal variation features in an integrated manner, and the latter is used to improve learning quality and training efficiency. Finally, the effectiveness of our method is verified by multiple experiments.
KW - Bidirectional Dilated Convolution
KW - Dynamic Graph Learning
KW - Graph Attention Networks
KW - Temporal Variation Matrix
KW - Time-series
UR - https://www.scopus.com/pages/publications/85185403870
U2 - 10.1109/ICDM58522.2023.00167
DO - 10.1109/ICDM58522.2023.00167
M3 - 会议稿件
AN - SCOPUS:85185403870
T3 - Proceedings - IEEE International Conference on Data Mining, ICDM
SP - 1313
EP - 1318
BT - Proceedings - 23rd IEEE International Conference on Data Mining, ICDM 2023
A2 - Chen, Guihai
A2 - Khan, Latifur
A2 - Gao, Xiaofeng
A2 - Qiu, Meikang
A2 - Pedrycz, Witold
A2 - Wu, Xindong
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 1 December 2023 through 4 December 2023
ER -