Predicting Temporal Sets with Deep Neural Networks

TL;DR

This paper introduces a deep neural network approach for predicting future sets in temporal sequences by modeling element relationships with graph convolutions and learning temporal dependencies through attention mechanisms, outperforming existing methods.

Contribution

The paper presents an integrated deep learning model that combines graph convolutions, attention mechanisms, and gated updates for improved temporal sets prediction.

Findings

Achieves competitive performance with limited training data.

Outperforms existing methods significantly.

Effectively models dynamic element relationships.

Abstract

Given a sequence of sets, where each set contains an arbitrary number of elements, the problem of temporal sets prediction aims to predict the elements in the subsequent set. In practice, temporal sets prediction is much more complex than predictive modelling of temporal events and time series, and is still an open problem. Many possible existing methods, if adapted for the problem of temporal sets prediction, usually follow a two-step strategy by first projecting temporal sets into latent representations and then learning a predictive model with the latent representations. The two-step approach often leads to information loss and unsatisfactory prediction performance. In this paper, we propose an integrated solution based on the deep neural networks for temporal sets prediction. A unique perspective of our approach is to learn element relationship by constructing set-level co-occurrence graph and then perform graph convolutions on the dynamic relationship graphs. Moreover, we design an attention-based module to adaptively learn the temporal dependency of elements and sets. Finally, we provide a gated updating mechanism to find the hidden shared patterns in different sequences and fuse both static and dynamic information to improve the prediction performance. Experiments on real-world data sets demonstrate that our approach can achieve competitive performances even with a portion of the training data and can outperform existing methods with a significant margin.