Uncertainty on Asynchronous Time Event Prediction

Abstract

Asynchronous event sequences are the basis of many applications throughout different industries. In this work, we tackle the task of predicting the next event (given a history), and how this prediction changes with the passage of time. Since at some time points (e.g. predictions far into the future) we might not be able to predict anything with confidence, capturing uncertainty in the predictions is crucial. We present two new architectures, WGP-LN and FD-Dir, modelling the evolution of the distribution on the probability simplex with time-dependent logistic normal and Dirichlet distributions. In both cases, the combination of RNNs with either Gaussian process or function decomposition allows to express rich temporal evolution of the distribution parameters, and naturally captures uncertainty. Experiments on class prediction, time prediction and anomaly detection demonstrate the high performances of our models on various datasets compared to other approaches.

Neurips 2019 (Spotlight)

References in corpus (3)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Bayesian Recurrent Neural Networks
• Approximating with Gaussians

Cited by in corpus (5)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
• Intensity-Free Learning of Temporal Point Processes
• Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation
• Fast and Flexible Temporal Point Processes with Triangular Maps