Joint Modeling of Event Sequence and Time Series with Attentional Twin Recurrent Neural Networks

Abstract

A variety of real-world processes (over networks) produce sequences of data whose complex temporal dynamics need to be studied. More especially, the event timestamps can carry important information about the underlying network dynamics, which otherwise are not available from the time-series evenly sampled from continuous signals. Moreover, in most complex processes, event sequences and evenly-sampled times series data can interact with each other, which renders joint modeling of those two sources of data necessary. To tackle the above problems, in this paper, we utilize the rich framework of (temporal) point processes to model event data and timely update its intensity function by the synergic twin Recurrent Neural Networks (RNNs). In the proposed architecture, the intensity function is synergistically modulated by one RNN with asynchronous events as input and another RNN with time series as input. Furthermore, to enhance the interpretability of the model, the attention mechanism for the neural point process is introduced. The whole model with event type and timestamp prediction output layers can be trained end-to-end and allows a black-box treatment for modeling the intensity. We substantiate the superiority of our model in synthetic data and three real-world benchmark datasets.

arXiv comment14 pages

References in corpus (9)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• DRAW: A Recurrent Neural Network For Image Generation
• A survey of random processes with reinforcement
• Learning Granger Causality for Hawkes Processes
• COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution
• Distilling Information Reliability and Source Trustworthiness from Digital Traces
• Multistage Campaigning in Social Networks
• From Micro to Macro: Uncovering and Predicting Information Cascading Process with Behavioral Dynamics
• Recurrent Poisson Factorization for Temporal Recommendation

Cited by in corpus (6)

• Deep Learning for Time Series Forecasting: Tutorial and Literature Survey
• The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process
• Robust and Subject-Independent Driving Manoeuvre Anticipation through Domain-Adversarial Recurrent Neural Networks
• Set Functions for Time Series
• Variational Inference of Joint Models using Multivariate Gaussian Convolution Processes
• Synthetic Event Time Series Health Data Generation