research-article

Open access

FlowGEN: A Generative Model for Flow Graphs

Authors:

Furkan Kocayusufoglu,

Ambuj K. SinghAuthors Info & Claims

KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

Pages 813 - 823

https://doi.org/10.1145/3534678.3539406

Published: 14 August 2022 Publication History

Abstract

Flow graphs capture the directed flow of a quantity of interest (e.g., water, power, vehicles) being transported through an underlying network. Modeling and generating realistic flow graphs is key in many applications in infrastructure design, transportation, and biomedical and social sciences. However, they pose a great challenge to existing generative models due to a complex dynamics that is often governed by domain-specific physical laws or patterns. We introduce FlowGEN, an implicit generative model for flow graphs, that learns how to jointly generate graph topologies and flows with diverse dynamics directly from data using a novel (flow) graph neural network. Experiments show that our approach is able to effectively reproduce relevant local and global properties of flow graphs, including flow conservation, cyclic trends, and congestion around hotspots.

References

[1]

Réka Albert and Albert-László Barabási. Statistical mechanics of complex networks. Reviews of modern physics, 74(1):47, 2002.

[2]

Martin Arjovsky, Soumith Chintala, and Léon Bottou. Wasserstein generative adversarial networks. In ICML, 2017.

Digital Library

[3]

Aleix Bassolas et al. Hierarchical organization of urban mobility and its connection with city livability. Nature communications, 10(1):1--10, 2019.

[4]

Mikhail Belkin and Partha Niyogi. Laplacian eigenmaps for dimensionality reduction and data representation. Neural computation, 15(6):1373--1396, 2003.

Digital Library

[5]

Aleksandar Bojchevski, Oleksandr Shchur, Daniel Zügner, and Stephan Günnemann. Netgan: Generating graphs via random walks. In ICML, 2018.

[6]

Alberto Bressan et al. Flows on networks: recent results and perspectives. EMS Surveys in Mathematical Sciences, 1(1):47--111, 2014.

[7]

Marc Brockschmidt et al. Generative code modeling with graphs. In ICLR, 2019.

[8]

Francesco Calabrese, Giusy Di Lorenzo, et al. Estimating origin-destination flows using mobile phone location data. IEEE Pervasive Computing, (4):36--44, 2011.

[9]

Matteo Chinazzi et al. The effect of travel restrictions on the spread of the 2019 novel coronavirus (covid-19) outbreak. Science, 368(6489):395--400, 2020.

[10]

Hang Chu, Daiqing Li, et al. Neural turtle graphics for modeling city road layouts. In ICCV, 2019.

[11]

Hanjun Dai et al. Scalable deep generative modeling for sparse graphs. In ICML, 2020.

[12]

Hermann W Dommel and William F Tinney. Optimal power flow solutions. IEEE Transactions on power apparatus and systems, (10):1866--1876, 1968.

[13]

Florian Dörfler et al. Electrical networks and algebraic graph theory: Models, properties, and applications. Proceedings of the IEEE, 106(5):977--1005, 2018.

[14]

Florian Dörfler and Francesco Bullo. Synchronization in complex networks of phase oscillators: A survey. Automatica, 50(6):1539--1564, 2014.

[15]

Paul Erdös and Alfréd Rényi. On random graphs. Publicationes mathematicae, 6(26):290--297, 1959.

[16]

M. Garavello and B. Piccoli. Traffic Flow on Networks: Conservation Laws Model. AIMS series on applied mathematics. AIMS, 2006.

[17]

Justin Gilmer, Samuel S Schoenholz, Patrick F Riley, Oriol Vinyals, and George E Dahl. Neural message passing for quantum chemistry. In ICML, 2017.

Digital Library

[18]

Ian Goodfellow et al. Generative adversarial nets. In NeurIPS, 2014.

[19]

Nikhil Goyal et al. Graphgen: a scalable approach to domain-agnostic labeled graph generation. In Proceedings of The Web Conference 2020, 2020.

[20]

Aditya Grover, Aaron Zweig, and Stefano Ermon. Graphite: Iterative generative modeling of graphs. In ICML, 2019.

[21]

Ishaan Gulrajani et al. Improved training of wasserstein gans. In NeurIPS, 2017.

[22]

Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In CVPR, 2016.

[23]

D.J. Hill and Guanrong Chen. Power systems as dynamic networks. In 2006 IEEE International Symposium on Circuits and Systems, 2006.

[24]

Jonas Hörsch et al. Pypsa-eur: An open optimisation model of the european transmission system. Energy strategy reviews, 22:207--215, 2018.

[25]

Junteng Jia, Michael T Schaub, Santiago Segarra, and Austin R Benson. Graph-based semi-supervised & active learning for edge flows. In KDD, 2019.

[26]

Wengong Jin, Regina Barzilay, and Tommi Jaakkola. Junction tree variational autoencoder for molecular graph generation. In ICML, 2018.

[27]

Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.

[28]

Diederik P Kingma and Max Welling. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.

[29]

Ryan Kinney et al. Modeling cascading failures in the north american power grid. The European Physical Journal B-Condensed Matter and Complex Systems, 46(1):101--107, 2005.

[30]

Thomas N Kipf and Max Welling. Variational graph auto-encoders. NIPS Workshop on Bayesian Deep Learning, 2016.

[31]

Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In ICLR, 2017.

[32]

Yujia Li et al. Learning deep generative models of graphs. arXiv preprint arXiv:1803.03324, 2018.

[33]

Yujia Li, Daniel Tarlow, Marc Brockschmidt, and Richard Zemel. Gated graph sequence neural networks. In ICLR, 2016.

[34]

Renjie Liao et al. Efficient graph generation with graph recurrent attention networks. In NeurIPS, 2019.

[35]

Jenny Liu, Aviral Kumar, Jimmy Ba, Jamie Kiros, and Kevin Swersky. Graph normalizing flows. In NeurIPS, 2019.

[36]

Mark EJ Newman. Mixing patterns in networks. Physical review E, 2003.

[37]

Chenhao Niu et al. Permutation invariant graph generation via score-based generative modeling. In AISTATS, 2020.

[38]

J. D. Orth, I. Thiele, and B. Ø. Palsson. What is flux balance analysis? Nat Biotechnol, 28(3):245--248, Mar 2010.

[39]

Chence Shi et al. Graphaf: a flow-based autoregressive model for molecular graph generation. In ICLR, 2020.

[40]

Arlei Silva et al. Combining physics and machine learning for network flow estimation. ICLR, 2021.

[41]

Martin Simonovsky and Nikos Komodakis. Graphvae: Towards generation of small graphs using variational autoencoders. In ICANN, 2018.

[42]

Yang Song and Stefano Ermon. Generative modeling by estimating gradients of the data distribution. In NeurIPS, 2019.

[43]

Akash Srivastava et al. Veegan: Reducing mode collapse in gans using implicit variational learning. In NeurIPS, 2017.

[44]

Lucas Theis, Aäron van den Oord, and Matthias Bethge. A note on the evaluation of generative models. arXiv preprint arXiv:1511.01844, 2015.

[45]

Petar Velivc ković et al. Graph attention networks. In ICLR, 2017.

[46]

Duncan J Watts and Steven H Strogatz. Collective dynamics of 'small-world'networks. Nature, 393(6684):440, 1998.

[47]

Carl Yang et al. Conditional structure generation through graph variational generative adversarial nets. In NeurIPS, 2019.

[48]

Jiaxuan You et al. Graphrnn: Generating realistic graphs with deep auto-regressive models. In ICML, 2018.

[49]

Xun Zheng et al. Dags with no tears: Continuous optimization for structure learning. In NeurIPS, 2018.

Cited By

Kazadi ADoss-Gollin JSilva ASalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)Pluvial flood emulation with hydraulics-informed message passingProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3693011(23367-23390)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3693011

Index Terms

FlowGEN: A Generative Model for Flow Graphs
1. Computing methodologies
  1. Artificial intelligence
    1. Knowledge representation and reasoning
      1. Spatial and physical reasoning
  2. Machine learning
    1. Machine learning approaches
      1. Learning latent representations

Recommendations

Two flow network simplification algorithms

Flow network simplification can reduce the size of the flow network and hence the amount of computation performed by flow algorithms. We present the first linear time algorithm for the undirected network case. We also give an O(|E|*(|V|+|E|)) time ...
Fast Augmentation Algorithms for Maximising the Flow in Repairable Flow Networks After a Component Failure
CIT '11: Proceedings of the 2011 IEEE 11th International Conference on Computer and Information Technology

The paper discuses new, very efficient augmentation algorithms and theorems related to maximising the flow in single-commodity and multi-commodity networks. For the first time, efficient algorithms with linear average running time O(m) in the size m of ...
GRAN Is Superior to GraphRNN: Node Orderings, Kernel- and Graph Embeddings-Based Metrics for Graph Generators
Machine Learning, Optimization, and Data Science
Abstract
A wide variety of generative models for graphs have been proposed. They are used in drug discovery, road networks, neural architecture search, and program synthesis. Generating graphs has theoretical challenges, such as isomorphic representations –...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

August 2022

5033 pages

ISBN:9781450393850

DOI:10.1145/3534678

General Chairs:
Aidong Zhang
University of Virginia
,
Huzefa Rangwala
Amazon/George Mason University

Copyright © 2022 Owner/Author.

This work is licensed under a Creative Commons Attribution International 4.0 License.

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 14 August 2022

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Conference

KDD '22

Sponsor:

KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

August 14 - 18, 2022

Washington DC, USA

Acceptance Rates

Overall Acceptance Rate 1,133 of 8,635 submissions, 13%

Upcoming Conference

KDD '25

Sponsor:
sigkdd
sigkdd

The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining

August 3 - 7, 2025

Toronto , ON , Canada

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
1,150
Total Downloads

Downloads (Last 12 months)365
Downloads (Last 6 weeks)53

Reflects downloads up to 28 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Kazadi ADoss-Gollin JSilva ASalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)Pluvial flood emulation with hydraulics-informed message passingProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3693011(23367-23390)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3693011

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Figures

Tables

Media

View Table of Conten