An embedding-based distance for temporal graphs
Not on the map. Why?
Abstract (arXiv)
Temporal graphs are commonly used to represent time-resolved relations between entities in many natural and artificial systems. Many techniques were devised to investigate the evolution of temporal graphs by comparing their state at different time points. However, quantifying the similarity between temporal graphs as a whole is an open problem. Here, we use embeddings based on time-respecting random walks to introduce a new notion of distance between temporal graphs. This distance is well-defined for pairs of temporal graphs with different numbers of nodes and different time spans. We study the case of a matched pair of graphs, when a known relation exists between their nodes, and the case of unmatched graphs, when such a relation is unavailable and the graphs may be of different sizes. We use empirical and synthetic temporal network data to show that the distance we introduce discriminates graphs with different topological and temporal properties. We provide an efficient implementation of the distance computation suitable for large-scale temporal graphs.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 32 of its 99 references that are in the map. First posted on arXiv 23 Jan 2024.
Builds on
32 of 99 references.
References · 32
- 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 399
- 2017A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applicationscited by 260
- 2017Graph Embedding Techniques, Applications, and Performance: A Surveycited by 188
- 2020Parametric UMAP embeddings for representation and semi-supervised learningcited by 103
- 2021A Survey on Embedding Dynamic Graphscited by 60
- 2015Contact patterns in a high school: a comparison between data collected using wearable sensors, contact diaries and friendship surveyscited by 59
- 2018NetLSD: Hearing the Shape of a Graphcited by 51
- 2020Understanding graph embedding methods and their applicationscited by 50
- 2019Metrics for Graph Comparison: A Practitioner's Guidecited by 37
- 2020Deep Graph Generators: A Surveycited by 36
- 2019Deep Graph Similarity Learning: A Surveycited by 19
- 2013DELTACON: A Principled Massive-Graph Similarity Functioncited by 17
20 more
- 2014Contact patterns among high school studentscited by 17
- 2017Can co-location be used as a proxy for face-to-face contacts?cited by 12
- 2013Detecting the community structure and activity patterns of temporal networks: a non-negative tensor factorization approachcited by 8
- 2017Community Discovery in Dynamic Networks: a Surveycited by 8
- 2018An information-theoretic, all-scales approach to comparing networkscited by 7
- 2020Network comparison and the within-ensemble graph distancecited by 7
- 2014Measuring large-scale social networks with high resolutioncited by 6
- 2016The Resistance Perturbation Distance: A Metric for the Analysis of Dynamic Networkscited by 5
- 2020Community detection in sparse time-evolving graphs with a dynamical Bethe-Hessiancited by 4
- 2018Detecting sequences of system states in temporal networkscited by 3
- 2020Gender and collaboration patterns in a temporal scientific authorship networkcited by 3
- 2013Temporal networks of face-to-face human interactionscited by 2
- 2018Comparing Temporal Graphs Using Dynamic Time Warpingcited by 2
- 2019Detecting social (in)stability in primates from their temporal co-presence networkcited by 2
- 2021Measuring and utilizing temporal network dissimilaritycited by 2
- 2015Exploring Temporal Networks with Greedy Walkscited by 1
- 2018Graph Distance from the Topological View of Non-backtracking Cyclescited by 1
- 2020Dynamic core-periphery structure of information sharing networks in the entorhinal cortex and the hippocampuscited by 1
- 2020Privacy and Uniqueness of Neighborhoods in Social Networkscited by 1
- 2023Learning distributed representations with efficient SoftMax normalizationcited by 1
Built on by
Citing papers per year: 2025: 3.
3 papers.