Knowledge-Preserving Incremental Social Event Detection via Heterogeneous GNNs

01/21/2021
by   Yuwei Cao, et al.
15

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 the 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 the 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 experimental results demonstrate the superiority of KPGNN over various baselines.

READ FULL TEXT
research
02/20/2023

Heterogeneous Social Event Detection via Hyperbolic Graph Representations

Social events reflect the dynamics of society and, here, natural disaste...
research
07/24/2019

Tripartite Heterogeneous Graph Propagation for Large-scale Social Recommendation

Graph Neural Networks (GNNs) have been emerging as a promising method fo...
research
04/02/2021

Streaming Social Event Detection and Evolution Discovery in Heterogeneous Information Networks

Events are happening in real-world and real-time, which can be planned a...
research
06/09/2019

Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networks

Events are happening in real-world and real-time, which can be planned a...
research
12/30/2021

Measuring and Sampling: A Metric-guided Subgraph Learning Framework for Graph Neural Network

Graph neural network (GNN) has shown convincing performance in learning ...
research
09/05/2022

Few-shot Incremental Event Detection

Event detection tasks can help people quickly determine the domain from ...

Please sign up or login with your details

Forgot password? Click here to reset