Knowledge-Preserving Incremental Social Event Detection via Heterogeneous GNNs

被引:64
作者
Cao, Yuwei [1 ]
Peng, Hao [2 ]
Wu, Jia [3 ]
Dou, Yingtong [1 ]
Li, Jianxin [2 ]
Yu, Philip S. [1 ]
机构
[1] Univ Illinois, Chicago, IL USA
[2] Beihang Univ, Beijing, Peoples R China
[3] Macquarie Univ, Sydney, NSW, Australia
来源
PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE 2021 (WWW 2021) | 2021年
关键词
Social Event Detection; Graph Neural Networks; Incremental Learning; Contrastive Learning;
D O I
10.1145/3442381.3449834
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:3383 / 3395
页数:13
相关论文
共 46 条
[1]  
[Anonymous], 2020, P PAKDD SPRING, DOI DOI 10.1007/978-3-030-47436-2_30
[2]  
[Anonymous], 2019, P NEURIPS
[3]  
[Anonymous], 2012, SDM
[4]  
Belghazi MI, 2018, PR MACH LEARN RES, V80
[5]   Latent Dirichlet allocation [J].
Blei, DM ;
Ng, AY ;
Jordan, MI .
JOURNAL OF MACHINE LEARNING RESEARCH, 2003, 3 (4-5) :993-1022
[6]   Learning Dynamic Context Graphs for Predicting Social Events [J].
Deng, Songgaojun ;
Rangwala, Huzefa ;
Ning, Yue .
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2019, :1007-1016
[7]  
Devlin J, 2019, 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, P4171
[8]  
Ester M., 1996, P 2 INT C KNOWLEDGE, P226, DOI DOI 10.5555/3001460.3001507
[9]   Normalized Mutual Information Feature Selection [J].
Estevez, Pablo. A. ;
Tesmer, Michel ;
Perez, Claudio A. ;
Zurada, Jacek A. .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2009, 20 (02) :189-201
[10]   Real-time Event Detection on Social Data Streams [J].
Fedoryszak, Mateusz ;
Frederick, Brent ;
Rajaram, Vijay ;
Zhong, Changtao .
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2019, :2774-2782