.png){kind=icon}
返回
Sparse-Dyn: Sparse dynamic graph multirepresentation learning via event-based sparse temporal attention network
.png){kind=icon}
OA
AI
DOI：10.1002/int.22967.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Dynamic graph neural networks (DGNNs) have been widely used in modeling and representation learning of graph structure data. Current dynamic representation learning focuses on either discrete learning which results in temporal information loss, or continuous learning which involves heavy computation. In this study, we proposed a novel DGNN, sparse dynamic (Sparse-Dyn). It adaptively encodes temporal information into a sequence of patches with an equal amount of temporal-topological structure. Therefore, while avoiding using snapshots which cause information loss, it also achieves a finer time granularity, which is close to what continuous networks could provide. In addition, we also designed a lightweight module, Sparse Temporal Transformer, to compute node representations through structural neighborhoods and temporal dynamics. Since the fully connected attention conjunction is simplified, the computation cost is far lower than the current state-of-the-art. Link prediction experiments are conducted on both continuous and discrete graph data sets. By comparing several state-of-the-art graph embedding baselines, the experimental results demonstrate that Sparse-Dyn has a faster inference speed while having competitive performance.
Keyword:
adaptive data encoding
dynamic graph neural network
link prediction
sparse temporal transformer
期刊
IF:
3.7
论文数:
3.1K
被引数:
8.1K
机构
引用论文
Resource Allocation in IoT Edge Computing via Concurrent Federated Reinforcement Learning基于并发联合强化学习的物联网边缘计算资源分配
PREAI
分享收藏Conjugated heat transfer and temperature distributions in a gas turbine combustion liner under base-load operation基本负荷运行下燃气轮机燃烧衬里中的共轭传热和温度分布
PREAI
分享收藏The Late Eocene House Range Flora, Sevier Desert, Utah: Paleoclimate and Paleoelevation.png)
PALAIOS
PALAIOSIF0
PREAI
分享收藏A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications图嵌入的综合调查: 问题，技术和应用
OAAI
OAAI分享收藏Faces are Protected as Privacy: An Automatic Tagging Framework Against Unpermitted Photo Sharing in Social MediaIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏分享收藏Dendritic mechanisms controlling the threshold and timing requirement of synaptic plasticityHippocampus
HippocampusIF0
PREAI
分享收藏
查看更多内容