Temporal Graph Offset Reconstruction: Towards Temporally Robust Graph Representation Learning
This work addresses the challenge of making accurate predictions in temporal graphs for applications like social network analysis or recommendation systems, though it is incremental as it builds on existing graph convolutional networks and auto-encoder concepts.
The paper tackles the problem of predicting future states in dynamic graphs by introducing a novel training procedure and unsupervised model that optimizes graph representations for future link prediction, achieving a 38% improvement over non-temporal baselines on a real-world dataset.
Graphs are a commonly used construct for representing relationships between elements in complex high dimensional datasets. Many real-world phenomenon are dynamic in nature, meaning that any graph used to represent them is inherently temporal. However, many of the machine learning models designed to capture knowledge about the structure of these graphs ignore this rich temporal information when creating representations of the graph. This results in models which do not perform well when used to make predictions about the future state of the graph -- especially when the delta between time stamps is not small. In this work, we explore a novel training procedure and an associated unsupervised model which creates graph representations optimised to predict the future state of the graph. We make use of graph convolutional neural networks to encode the graph into a latent representation, which we then use to train our temporal offset reconstruction method, inspired by auto-encoders, to predict a later time point -- multiple time steps into the future. Using our method, we demonstrate superior performance for the task of future link prediction compared with none-temporal state-of-the-art baselines. We show our approach to be capable of outperforming non-temporal baselines by 38% on a real world dataset.