Multi-Task Decouple Learning With Hierarchical Attentive Point Process
- 17 August 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (4) , 1741-1757
Abstract
Sequential data mining is ubiquitous in various scenarios. Modeling event sequence and predicting event occurrence is of vital importance in sequential data mining, and Temporal Point Processes (TPP) are widely used in this area. Conventional TPP use objective functions as sum of classification loss for event type and regression loss for occurrence time, leading to practical limitations that conventional TPP is unable to predict the occurrence of each type of event and distinguish the dependency within and between different event types. To tackle these defects, we propose a Multi-task Decouple Learning (MTDL) framework to model TPP from a novel perspective of Multi-task Learning (MTL), i.e. predicting the next-step occurrence time for all event types using a weighted multi-task regression loss. We experiment with three state-of-the-arts, showing that the proposed MTDL framework can improve the performance of original TPP models. Moreover, we develop a Hierarchical Attentive Point Process (HAPP) to further exploit the potential of the proposed MTDL framework, using a hierarchical attention mechanism to capture the inner-sequence time dependency within the same type of events and the inter-sequence dependency between different types of events. Experiments on real-world business dataset and public datasets show the efficacy of the proposed method.Keywords
This publication has 34 references indexed in Scilit:
- Multi-task learning for spatial events prediction from social dataInformation Sciences, 2021
- A Survey on Multi-Task LearningIEEE Transactions on Knowledge and Data Engineering, 2021
- Modeling Event Propagation via Graph Biased Temporal Point ProcessIEEE Transactions on Neural Networks and Learning Systems, 2020
- Taskonomy: Disentangling Task Transfer Learning2018
- Patient Flow Prediction via Discriminative Learning of Mutually-Correcting ProcessesIEEE Transactions on Knowledge and Data Engineering, 2016
- Modeling E-mail Networks and Inferring Leadership Using Self-Exciting Point ProcessesJournal of the American Statistical Association, 2016
- SEISMIC2015
- Quantifying Long-Term Scientific ImpactScience, 2013
- Point process modelling of the Afghan War DiaryProceedings of the National Academy of Sciences, 2012
- Reconstruction of missing data in social networks based on temporal patterns of interactionsInverse Problems, 2011