Knowledge-Preserving Incremental Social Event Detection via Heterogeneous GNNs

TL;DR

This paper introduces KPGNN, a novel GNN-based method for incremental social event detection that preserves knowledge, adapts to streaming data, and leverages social graph structures for improved accuracy.

Contribution

The paper proposes KPGNN, a knowledge-preserving incremental GNN that models social messages as graphs, uses contrastive loss for adaptation, and employs scalable training strategies.

Findings

KPGNN outperforms baseline methods in accuracy.

It effectively preserves and extends knowledge over time.

The approach handles large social streams efficiently.

Abstract

Social events provide valuable insights into group social behaviors and public concerns and therefore have many applications in fields such as product recommendation and crisis management. The complexity and streaming nature of social messages make it appealing to address social event detection in an incremental learning setting, where acquiring, preserving, and extending knowledge are major concerns. Most existing methods, including those based on incremental clustering and community detection, learn limited amounts of knowledge as they ignore the rich semantics and structural information contained in social data. Moreover, they cannot memorize previously acquired knowledge. In this paper, we propose a novel Knowledge-Preserving Incremental Heterogeneous Graph Neural Network (KPGNN) for incremental social event detection. To acquire more knowledge, KPGNN models complex social messages into unified social graphs to facilitate data utilization and explores the expressive power of GNNs for knowledge extraction. To continuously adapt to the incoming data, KPGNN adopts contrastive loss terms that cope with a changing number of event classes. It also leverages the inductive learning ability of GNNs to efficiently detect events and extends its knowledge from previously unseen data. To deal with large social streams, KPGNN adopts a mini-batch subgraph sampling strategy for scalable training, and periodically removes obsolete data to maintain a dynamic embedding space. KPGNN requires no feature engineering and has few hyperparameters to tune. Extensive experiment results demonstrate the superiority of KPGNN over various baselines.