NPGLM: A Non-Parametric Method for Temporal Link Prediction

TL;DR

This paper introduces NP-GLM, a non-parametric probabilistic approach for predicting the timing of future links in information networks based on current features, validated through experiments on synthetic and real data.

Contribution

The paper presents a novel non-parametric method, NP-GLM, for temporal link prediction that infers the probability distribution of link appearance times from features.

Findings

NP-GLM outperforms baseline methods in experiments.

Effective on both synthetic and real-world data.

Provides a probabilistic framework for temporal link prediction.

Abstract

In this paper, we try to solve the problem of temporal link prediction in information networks. This implies predicting the time it takes for a link to appear in the future, given its features that have been extracted at the current network snapshot. To this end, we introduce a probabilistic non-parametric approach, called "Non-Parametric Generalized Linear Model" (NP-GLM), which infers the hidden underlying probability distribution of the link advent time given its features. We then present a learning algorithm for NP-GLM and an inference method to answer time-related queries. Extensive experiments conducted on both synthetic data and real-world Sina Weibo social network demonstrate the effectiveness of NP-GLM in solving temporal link prediction problem vis-a-vis competitive baselines.