Sequential Edge Clustering in Temporal Multigraphs

TL;DR

This paper introduces a dynamic nonparametric model for temporal multigraphs that captures both sparsity and evolving clustering patterns, improving predictive performance over existing models.

Contribution

The paper proposes a novel dynamic nonparametric model that integrates temporal dynamics with structured sparsity in interaction graphs, enhancing modeling capabilities.

Findings

Improved held-out likelihood compared to stationary models

Enhanced predictive performance on dynamic interaction graphs

Effectively captures reinforcement of recent behavioral patterns

Abstract

Interaction graphs, such as those recording emails between individuals or transactions between institutions, tend to be sparse yet structured, and often grow in an unbounded manner. Such behavior can be well-captured by structured, nonparametric edge-exchangeable graphs. However, such exchangeable models necessarily ignore temporal dynamics in the network. We propose a dynamic nonparametric model for interaction graphs that combine the sparsity of the exchangeable models with dynamic clustering patterns that tend to reinforce recent behavioral patterns. We show that our method yields improved held-out likelihood over stationary variants, and impressive predictive performance against a range of state-of-the-art dynamic interaction graph models.