DyGCL: Dynamic Graph Contrastive Learning For Event Prediction

TL;DR

DyGCL introduces a contrastive learning framework that captures both local and global dynamic graph representations for improved event prediction from textual data.

Contribution

The paper proposes a novel DyGCL model that integrates local and global graph encodings with contrastive learning for more accurate event forecasting.

Findings

Outperforms baseline methods on six real-world datasets

Effectively captures evolving local and global graph structures

Enhances event prediction accuracy through hierarchical representations

Abstract

Predicting events such as political protests, flu epidemics, and criminal activities is crucial to proactively taking necessary measures and implementing required responses to address emerging challenges. Capturing contextual information from textual data for event forecasting poses significant challenges due to the intricate structure of the documents and the evolving nature of events. Recently, dynamic Graph Neural Networks (GNNs) have been introduced to capture the dynamic patterns of input text graphs. However, these models only utilize node-level representation, causing the loss of the global information from graph-level representation. On the other hand, both node-level and graph-level representations are essential for effective event prediction as node-level representation gives insight into the local structure, and the graph-level representation provides an understanding of the global structure of the temporal graph. To address these challenges, in this paper, we propose a Dynamic Graph Contrastive Learning (DyGCL) method for event prediction. Our model DyGCL employs a local view encoder to learn the evolving node representations, which effectively captures the local dynamic structure of input graphs. Additionally, it harnesses a global view encoder to perceive the hierarchical dynamic graph representation of the input graphs. Then we update the graph representations from both encoders using contrastive learning. In the final stage, DyGCL combines both representations using an attention mechanism and optimizes its capability to predict future events. Our extensive experiment demonstrates that our proposed method outperforms the baseline methods for event prediction on six real-world datasets.