Filtration-Based Representation Learning for Temporal Graphs

TL;DR

This paper presents a novel filtration method for temporal graphs using $$-temporal motifs, enabling multi-scale analysis with tools like persistent homology, and demonstrates its effectiveness in classification tasks.

Contribution

It introduces a filtration technique based on $$-temporal motifs for temporal graphs, allowing existing static graph tools to analyze temporal structures.

Findings

Effective in temporal graph classification tasks

Enables application of static graph tools to temporal data

Provides multi-scale representation of temporal structures

Abstract

In this work, we introduce a filtration on temporal graphs based on $\delta$-temporal motifs (recurrent subgraphs), yielding a multi-scale representation of temporal structure. Our temporal filtration allows tools developed for filtered static graphs, including persistent homology and recent graph filtration kernels, to be applied directly to temporal graph analysis. We demonstrate the effectiveness of this approach on temporal graph classification tasks.