Sparse‐Dyn: Sparse dynamic graph multirepresentation learning via event‐based sparse temporal attention network. Issue 11 (25th July 2022)

• Record Type: Journal Article
• Authors: Pang, Yan; Shan, Ai; Wang, Zhen; Wang, Mengyu; Li, Jianwei; Zhang, Ji; Huang, Teng; Liu, Chao
• Is Part Of: International journal of intelligent systems. Volume 37:Issue 11(2022)
• Page Start: 8770
• Page End: 8789
• Publication Date: 2022-07-25
• Subjects: adaptive data encoding -- dynamic graph neural network -- link prediction -- sparse temporal transformer; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; 006.3
• DOI: 10.1002/int.22967
• Languages: English
• ISSNs: 0884-8173

Abstract

Abstract: 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.