Exploiting Spatial-Temporal Data in Knowledge Graphs for Enhanced Prediction

Ruiyi Yang, Flora D. Salim, Hao Xue

Keywords: Knowledge graph, spatial-temporal data

TL;DR: A novel framework of constructing and exploring Spatial-temporal knowledge graph for prediction

Abstract:

Knowledge graphs (KGs) have been increasingly employed for link prediction and recommendation using real-world datasets. However, the majority of current methods rely on static data, neglecting the dynamic nature and the hidden spatial-temporal attributes of real-world scenarios. This often results in suboptimal predictions and recommendations. Although there are effective spatial-temporal inference methods, they face challenges such as scalability with large datasets and inadequate semantic understanding, which impede their performance.
To address these limitations, this paper introduces a novel framework for constructing and exploring spatial-temporal KGs. Our approach seamlessly integrates spatial and temporal data to form KGs. We further exploit these KGs through a new 3-step embeddings method. These embeddings can be used for future temporal sequence prediction and spatial information recommendation, providing valuable insights for various applications such as retail sales forecasting and traffic volume prediction. By integrating spatial-temporal data into KGs, our framework offers a more comprehensive understanding of the underlying patterns and trends, thereby enhancing the accuracy of predictions and the relevance of recommendations. This work paves the way for more effective utilization of spatial-temporal data in KGs, with potential impacts across a wide range of sectors.

Track: COI (submissions co-authored by SAC)

Submission Guidelines Scope: Yes

Submission Guidelines Blind: Yes

Submission Guidelines Format: Yes

Submission Guidelines Limit: Yes

Submission Guidelines Authorship: Yes

Student Author: Yes

Submission Number: 697