Addressing Mark Imbalance in Integration-free Neural Marked Temporal Point Processes
This work addresses a specific challenge in event prediction for domains with imbalanced event types, representing an incremental improvement over existing methods.
The paper tackles the problem of mark imbalance in marked temporal point processes, which harms prediction for rare marks, by proposing a thresholding method that adjusts mark probabilities based on prior probabilities and a novel neural model for efficient time sampling. Experiments show superior performance in next event mark and time prediction on real-world datasets.
Marked Temporal Point Process (MTPP) has been well studied to model the event distribution in marked event streams, which can be used to predict the mark and arrival time of the next event. However, existing studies overlook that the distribution of event marks is highly imbalanced in many real-world applications, with some marks being frequent but others rare. The imbalance poses a significant challenge to the performance of the next event prediction, especially for events of rare marks. To address this issue, we propose a thresholding method, which learns thresholds to tune the mark probability normalized by the mark's prior probability to optimize mark prediction, rather than predicting the mark directly based on the mark probability as in existing studies. In conjunction with this method, we predict the mark first and then the time. In particular, we develop a novel neural MTPP model to support effective time sampling and estimation of mark probability without computationally expensive numerical improper integration. Extensive experiments on real-world datasets demonstrate the superior performance of our solution against various baselines for the next event mark and time prediction. The code is available at https://github.com/undes1red/IFNMTPP.