A Regularization Approach for Prediction of Edges and Node Features in Dynamic Graphs

TL;DR

This paper introduces a hybrid regularization method that jointly predicts dynamic graph structures and node features, leveraging their interdependence to improve prediction accuracy on synthetic and real datasets.

Contribution

It proposes a novel joint regularization framework that simultaneously learns graph evolution and node features, enhancing predictive performance.

Findings

Joint regularization outperforms separate methods in prediction accuracy.

The approach is effective on both synthetic and real data.

Improved prediction of graph links and node features observed.

Abstract

We consider the two problems of predicting links in a dynamic graph sequence and predicting functions defined at each node of the graph. In many applications, the solution of one problem is useful for solving the other. Indeed, if these functions reflect node features, then they are related through the graph structure. In this paper, we formulate a hybrid approach that simultaneously learns the structure of the graph and predicts the values of the node-related functions. Our approach is based on the optimization of a joint regularization objective. We empirically test the benefits of the proposed method with both synthetic and real data. The results indicate that joint regularization improves prediction performance over the graph evolution and the node features.