TY - GEN
T1 - From known to unknown
T2 - 31st ACM International Conference on Information and Knowledge Management, CIKM 2022
AU - Ren, Jiaqian
AU - Jiang, Lei
AU - Peng, Hao
AU - Cao, Yuwei
AU - Wu, Jia
AU - Yu, Philip S.
AU - He, Lifang
N1 - Copyright the Author(s) 2022. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.
PY - 2022/10
Y1 - 2022/10
N2 - State-of-the-art Graph Neural Networks (GNNs) have achieved tremendous success in social event detection tasks when restricted to a closed set of events. However, considering the large amount of data needed for training and the limited ability of a neural network in handling previously unknown data, it is hard for existing GNN-based methods to operate in an open set setting. To address this problem, we design a Quality-aware Self-improving Graph Neural Network (QSGNN) which extends the knowledge from known to unknown by leveraging the best of known samples and reliable knowledge transfer. Specifically, to fully exploit the labeled data, we propose a novel supervised pairwise loss with an additional orthogonal inter-class relation constraint to train the backbone GNN encoder. The learnt, already-known events further serve as strong reference bases for the unknown ones, which greatly prompts knowledge acquisition and transfer. When the model is generalized to unknown data, to ensure the effectiveness and reliability, we further leverage the reference similarity distribution vectors for pseudo pairwise label generation, selection and quality assessment. Following the diversity principle of active learning, our method selects diverse pair samples with the generated pseudo labels to fine-tune the GNN encoder. Besides, we propose a novel quality-guided optimization in which the contributions of pseudo labels are weighted based on consistency. Experimental results validate that our model achieves state-of-the-art results and extends well to unknown events.
AB - State-of-the-art Graph Neural Networks (GNNs) have achieved tremendous success in social event detection tasks when restricted to a closed set of events. However, considering the large amount of data needed for training and the limited ability of a neural network in handling previously unknown data, it is hard for existing GNN-based methods to operate in an open set setting. To address this problem, we design a Quality-aware Self-improving Graph Neural Network (QSGNN) which extends the knowledge from known to unknown by leveraging the best of known samples and reliable knowledge transfer. Specifically, to fully exploit the labeled data, we propose a novel supervised pairwise loss with an additional orthogonal inter-class relation constraint to train the backbone GNN encoder. The learnt, already-known events further serve as strong reference bases for the unknown ones, which greatly prompts knowledge acquisition and transfer. When the model is generalized to unknown data, to ensure the effectiveness and reliability, we further leverage the reference similarity distribution vectors for pseudo pairwise label generation, selection and quality assessment. Following the diversity principle of active learning, our method selects diverse pair samples with the generated pseudo labels to fine-tune the GNN encoder. Besides, we propose a novel quality-guided optimization in which the contributions of pseudo labels are weighted based on consistency. Experimental results validate that our model achieves state-of-the-art results and extends well to unknown events.
KW - active learning
KW - contrastive learning
KW - graph neural network
KW - social event detection
UR - http://www.scopus.com/inward/record.url?scp=85140842807&partnerID=8YFLogxK
U2 - 10.1145/3511808.3557329
DO - 10.1145/3511808.3557329
M3 - Conference proceeding contribution
AN - SCOPUS:85140842807
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 1696
EP - 1705
BT - CIKM 2022 - Proceedings of the 31st ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery (ACM)
CY - New York, NY
Y2 - 17 October 2022 through 21 October 2022
ER -