Optimal transport distances for directed, weighted graphs: a case study with cell-cell communication networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nagai, James S., Costa, Ivan G., Schaub, Michael T.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909147265499136
author Nagai, James S.
Costa, Ivan G.
Schaub, Michael T.
author_facet Nagai, James S.
Costa, Ivan G.
Schaub, Michael T.
contents Comparing graphs by means of optimal transport has recently gained significant attention, as the distances induced by optimal transport provide both a principled metric between graphs as well as an interpretable description of the associated changes between graphs in terms of a transport plan. As the lack of symmetry introduces challenges in the typically considered formulations, optimal transport distances for graphs have mostly been developed for undirected graphs. Here, we propose two distance measures to compare directed graphs based on variants of optimal transport: (i) an earth movers distance (Wasserstein) and (ii) a Gromov-Wasserstein (GW) distance. We evaluate these two distances and discuss their relative performance for both simulated graph data and real-world directed cell-cell communication graphs, inferred from single-cell RNA-seq data.
format Preprint
id arxiv_https___arxiv_org_abs_2309_07030
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Optimal transport distances for directed, weighted graphs: a case study with cell-cell communication networks
Nagai, James S.
Costa, Ivan G.
Schaub, Michael T.
Machine Learning
Social and Information Networks
Systems and Control
Genomics
Molecular Networks
Comparing graphs by means of optimal transport has recently gained significant attention, as the distances induced by optimal transport provide both a principled metric between graphs as well as an interpretable description of the associated changes between graphs in terms of a transport plan. As the lack of symmetry introduces challenges in the typically considered formulations, optimal transport distances for graphs have mostly been developed for undirected graphs. Here, we propose two distance measures to compare directed graphs based on variants of optimal transport: (i) an earth movers distance (Wasserstein) and (ii) a Gromov-Wasserstein (GW) distance. We evaluate these two distances and discuss their relative performance for both simulated graph data and real-world directed cell-cell communication graphs, inferred from single-cell RNA-seq data.
title Optimal transport distances for directed, weighted graphs: a case study with cell-cell communication networks
topic Machine Learning
Social and Information Networks
Systems and Control
Genomics
Molecular Networks
url https://arxiv.org/abs/2309.07030