Link Prediction in Graphs with Autoregressive Features
This work addresses link prediction for dynamic graphs, but it appears incremental as it builds on existing autoregressive and optimization techniques without claiming broad breakthroughs.
The paper tackles link prediction in time-evolving graphs by assuming node features follow a vector autoregressive model and proposes a joint optimization method for adjacency and VAR matrices, resulting in derived oracle inequalities that illustrate trade-offs in parameter choices.
In the paper, we consider the problem of link prediction in time-evolving graphs. We assume that certain graph features, such as the node degree, follow a vector autoregressive (VAR) model and we propose to use this information to improve the accuracy of prediction. Our strategy involves a joint optimization procedure over the space of adjacency matrices and VAR matrices which takes into account both sparsity and low rank properties of the matrices. Oracle inequalities are derived and illustrate the trade-offs in the choice of smoothing parameters when modeling the joint effect of sparsity and low rank property. The estimate is computed efficiently using proximal methods through a generalized forward-backward agorithm.