Knowledge-Preserving Incremental Social Event Detection via Heterogeneous GNNs

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.

arXiv commentThis work has been accepted to The Web Conference 2021

References in corpus (12)

• Efficient Estimation of Word Representations in Vector Space
• FaceNet: A Unified Embedding for Face Recognition and Clustering
• Semi-Supervised Classification with Graph Convolutional Networks
• An overview of gradient descent optimization algorithms
• Inductive Representation Learning on Large Graphs
• In Defense of the Triplet Loss for Person Re-Identification
• Learning deep representations by mutual information estimation and maximization
• Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
• Graph Transformer Networks
• MINE: Mutual Information Neural Estimation
• Real-time Event Detection on Social Data Streams
• Can Graph Neural Networks Go "Online"? An Analysis of Pretraining and Inference

Cited by in corpus (11)

• A Comprehensive Survey on Community Detection with Deep Learning
• Fast Parallel Hypertree Decompositions in Logarithmic Recursion Depth
• Federated Social Recommendation with Graph Neural Network
• HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networks
• Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks
• Heterogeneous Social Event Detection via Hyperbolic Graph Representations
• An Anomaly Event Detection Method Based on GNN Algorithm for Multi-data Sources
• Adaptive Differentially Private Structural Entropy Minimization for Unsupervised Social Event Detection
• Event Extraction by Associating Event Types and Argument Roles
• Relevance-Aware Anomalous Users Detection in Social Network via Graph Neural Network
• Streaming Social Event Detection and Evolution Discovery in Heterogeneous Information Networks