Event Prediction
Event prediction focuses on forecasting the timing and type of future events using historical data, aiming to improve decision-making across various domains. Current research heavily utilizes large language models (LLMs) integrated with temporal point processes (TPPs) and graph neural networks, often employing techniques like parameter-efficient fine-tuning and attention mechanisms to enhance accuracy and efficiency. This field is significant for its potential to improve healthcare, finance, and risk management by enabling proactive interventions and informed resource allocation, with ongoing efforts to address challenges like data sparsity, incomplete information, and uncertainty quantification.
Papers
SMURF-THP: Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process
Zichong Li, Yanbo Xu, Simiao Zuo, Haoming Jiang, Chao Zhang, Tuo Zhao, Hongyuan Zha
Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process with Uncertainty Quantification
Zichong Li, Qunzhi Xu, Zhenghao Xu, Yajun Mei, Tuo Zhao, Hongyuan Zha