GLANet: temporal knowledge graph completion based on global and local information-aware network

• Published in: Applied intelligence (Dordrecht, Netherlands) Netherlands), 2023-08, Vol.53 (16), p.19285-19301
• Main Authors: Wang, Jingbin, Lin, Xinyu, Huang, Hao, Ke, Xifan, Wu, Renfei, You, Changkai, Guo, Kun
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Computer Science; Embedding; Evolution; Graph representations; Knowledge representation; Machines; Manufacturing; Mechanical Engineering; Neighborhoods; Network analysis; Performance prediction; Processes; Sparsity; Time series
• ISSN: 0924-669X; 1573-7497
• DOI: 10.1007/s10489-023-04481-z

Knowledge graph completion (KGC) has been widely explored, but the task of temporal knowledge graph completion (TKGC) for predicting future events is far from perfection. Some embedding-based approaches have achieved significant results on the TKGC task by modeling the structural information of each temporal snapshot and the evolution between temporal snapshots. However, due to the uneven distribution of data in knowledge graphs (KGs), models that only utilize local structure and time series information suffer from information sparsity, resulting in some entities failing to obtain a better embedding representation due to less available information. Moreover, existing methods usually do not distinguish between the time span and frequency of historical information, which reduces the performance of link prediction. For this reason, we propose the G lobal and L ocal Information- A ware N e t work (GL-ANet) to capture both global and local information. In particular, to model global information, we capture global structural information of entities across time using a global neighborhood aggregator to enrich the representation of entities; global historical information is obtained based on the frequency and time span of historical facts, focusing on recent and frequent events rather than all historical events to suggest the performance of link prediction; to model local information, we propose a two-layer attention network to capture local structural information at each timestamp, using a gating mechanism and GRU to capture local evolution information. Extensive experiments demonstrate the effectiveness of our model, achieving significant improvements and outperforming state-of-the-art models on five benchmark datasets.