Nonparametric Link Prediction in Dynamic Networks

TL;DR

This paper introduces a non-parametric method for link prediction in dynamic networks that leverages local neighborhood features, demonstrating superior performance especially in complex, fluctuating graph scenarios.

Contribution

It presents a novel non-parametric algorithm for dynamic link prediction that accounts for diverse neighborhood dynamics and proves its consistency with an efficient implementation.

Findings

Outperforms state-of-the-art methods on real-world data

Effective in scenarios with sharp fluctuations and non-linearities

Provides a consistent estimator with fast locality-sensitive hashing

Abstract

We propose a non-parametric link prediction algorithm for a sequence of graph snapshots over time. The model predicts links based on the features of its endpoints, as well as those of the local neighborhood around the endpoints. This allows for different types of neighborhoods in a graph, each with its own dynamics (e.g, growing or shrinking communities). We prove the consistency of our estimator, and give a fast implementation based on locality-sensitive hashing. Experiments with simulated as well as five real-world dynamic graphs show that we outperform the state of the art, especially when sharp fluctuations or non-linearities are present.