HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences
This addresses the under-investigated problem of long-horizon event sequence prediction, which is incremental as it builds on existing autoregressive models by adding a reweighting component.
The paper tackles the problem of long-horizon prediction of event sequences, where existing autoregressive models perform poorly, and proposes HYPRO, a hybridly normalized probabilistic model that significantly outperforms previous models in experiments on multiple real-world datasets.
In this paper, we tackle the important yet under-investigated problem of making long-horizon prediction of event sequences. Existing state-of-the-art models do not perform well at this task due to their autoregressive structure. We propose HYPRO, a hybridly normalized probabilistic model that naturally fits this task: its first part is an autoregressive base model that learns to propose predictions; its second part is an energy function that learns to reweight the proposals such that more realistic predictions end up with higher probabilities. We also propose efficient training and inference algorithms for this model. Experiments on multiple real-world datasets demonstrate that our proposed HYPRO model can significantly outperform previous models at making long-horizon predictions of future events. We also conduct a range of ablation studies to investigate the effectiveness of each component of our proposed methods.