Tracking network dynamics: A survey using graph distances

From longitudinal biomedical studies to social networks, graphs have emerged as essential objects for describing evolving interactions between agents in complex systems. In such studies, after pre-processing, the data are encoded by a set of graphs, each representing a system’s state at a different point in time or space. The analysis of the system’s dynamics depends on the selection of the appropriate analytical tools. In particular, after specifying properties characterizing similarities between states, a critical step lies in the choice of a distance between graphs capable of reflecting such similarities. While the literature offers a number of distances to choose from, their properties have been little investigated and no guidelines regarding the choice of such a distance have yet been provided. In particular, most graph distances consider that the nodes are exchangeable—ignoring node “identities.” Alignment of the graphs according to identified nodes enables us to enhance these distances’ sensitivity to perturbations in the network and detect important changes in graph dynamics. Thus the selection of an adequate metric is a decisive—yet delicate—practical matter. In the spirit of Goldenberg et al.’s seminal 2009 review [Found. Trends Mach. Learn. 2 (2010) 129–233], this article provides an overview of commonly-used graph distances and an explicit characterization of the structural changes that they are best able to capture. We show how these choices affect real-life situations, and we use these distances to analyze both a longitudinal microbiome dataset and a brain fMRI study. One contribution of the present study is a coordinated suite of data analytic techniques, displays and statistical tests using “metagraphs”: a graph of graphs based on a chosen metric. Permutation tests can uncover the effects of covariates on the graphs’ variability. Furthermore, synthetic examples provide intuition as to the qualities and drawbacks of the different distances. Above all, we provide some guidance on choosing one distance over another in different contexts. Finally, we extend the scope of our analyses from temporal to spatial dynamics and apply these different distances to a network created from worldwide recipes.

[1]  M. Levandowsky,et al.  Distance between Sets , 1971, Nature.

[2]  Alexander K. Kelmans.  Comparison of graphs by their number of spanning trees , 1976, Discret. Math..

[3]  Alexander K. Kelmans.  Transformations of a Graph Increasing its Laplacian Polynomial and Number of Spanning Trees , 1997, Eur. J. Comb..

[4]  Alexander S Mikhailov,et al.  Evolutionary reconstruction of networks. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[5]  J. Jost,et al.  Evolving networks with distance preferences. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[6]  Pierre-Antoine Champin,et al.  Measuring the Similarity of Labeled Graphs , 2003, ICCBR.

[7]  Patrick C Phillips,et al.  Network thinking in ecology and evolution. , 2005, Trends in ecology & evolution.

[8]  E. Mardis,et al.  An obesity-associated gut microbiome with increased capacity for energy harvest , 2006, Nature.

[9]  Fan Chung,et al.  The heat kernel as the pagerank of a graph , 2007, Proceedings of the National Academy of Sciences.

[10]  S. V. N. Vishwanathan,et al.  Graph kernels , 2007 .

[11]  Daniel A. Spielman,et al.  Spectral Graph Theory and its Applications , 2007, 48th Annual IEEE Symposium on Foundations of Computer Science (FOCS'07).

[12]  Anirban Banerjee,et al.  Spectral plot properties: Towards a qualitative classification of networks , 2008, Networks Heterog. Media.

[13]  George C. Verghese,et al.  Graph similarity scoring and matching , 2008, Appl. Math. Lett..

[14]  L. Fulton,et al.  Diet-induced obesity is linked to marked but reversible alterations in the mouse distal gut microbiome. , 2008, Cell host & microbe.

[15]  Edoardo M. Airoldi,et al.  A Survey of Statistical Network Models , 2009, Found. Trends Mach. Learn..

[16]  Pierre Vandergheynst,et al.  Wavelets on Graphs via Spectral Graph Theory , 2009, ArXiv.

[17]  Cesare Furlanello,et al.  An introduction to spectral distances in networks , 2010, WIRN.

[18]  Hector Garcia-Molina,et al.  Web graph similarity for anomaly detection , 2010, Journal of Internet Services and Applications.

[19]  D. Relman,et al.  Incomplete recovery and individualized responses of the human distal gut microbiota to repeated antibiotic perturbation , 2010, Proceedings of the National Academy of Sciences.

[20]  Ankur P. Parikh,et al.  Algorithms for Graph Similarity and Subgraph Matching , 2011 .

[21]  Christine L. Cox,et al.  Reduced Interhemispheric Resting State Functional Connectivity in Cocaine Addiction , 2011, Biological Psychiatry.

[22]  Albert-László Barabási,et al.  Flavor network and the principles of food pairing , 2011, Scientific reports.

[23]  Mario Thüne,et al.  Eigenvalues of Matrices and Graphs , 2012 .

[24]  Noah Fierer,et al.  Using network analysis to explore co-occurrence patterns in soil microbial communities , 2011, The ISME Journal.

[25]  Susan Holmes,et al.  Computational Tools for Evaluating Phylogenetic and Hierarchical Clustering Trees , 2010, Journal of computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America.

[26]  Susan P. Holmes,et al.  Comparisons of Distance Methods for Combining Covariates and Abundances in Microbiome Studies , 2011, Pacific Symposium on Biocomputing.

[27]  Dragoš Cvetković,et al.  Spectral recognition of graphs , 2012 .

[28]  Cesare Furlanello,et al.  A glocal distance for network comparison , 2012, ArXiv.

[29]  J. Lampe,et al.  The gut microbiome and obesity. , 2012, Nestle Nutrition Institute workshop series.

[30]  Pascal Frossard,et al.  The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains , 2012, IEEE Signal Processing Magazine.

[31]  Miquel A. Ferrer,et al.  Median Graph Computation by Means of Graph Embedding into Vector Spaces , 2013 .

[32]  Pierre Vandergheynst,et al.  Vertex-Frequency Analysis on Graphs , 2013, ArXiv.

[33]  Jean-Yves Ramel,et al.  Multilevel Analysis of Attributed Graphs for Explicit Graph Embedding in Vector Spaces , 2013 .

[34]  Robin Wilson,et al.  Modern Graph Theory , 2013 .

[35]  Anthony Bonato,et al.  Dimensionality of Social Networks Using Motifs and Eigenvalues , 2014, PloS one.

[36]  Georg K Gerber,et al.  The dynamic microbiome , 2014, FEBS letters.

[37]  Pierre Borgnat,et al.  Graph Wavelets for Multiscale Community Mining , 2014, IEEE Transactions on Signal Processing.

[38]  Christine L. Sun,et al.  Temporal and spatial variation of the human microbiota during pregnancy , 2015, Proceedings of the National Academy of Sciences.

[39]  Cesare Furlanello,et al.  The HIM glocal metric and kernel for network comparison and classification , 2012, 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[40]  C. Furlanello,et al.  Differential Network Analysis and Graph Classification: A Glocal Approach , 2016, 1602.00467.

[41]  Pascal Tétreault,et al.  Brain Connectivity Predicts Placebo Response across Chronic Pain Clinical Trials , 2016, PLoS biology.

[42]  P. Stadler,et al.  Spectral classes of regular, random, and empirical graphs , 2014, 1406.6454.

[43]  Sophie J. Weiss,et al.  Correlation detection strategies in microbial data sets vary widely in sensitivity and precision , 2016, The ISME Journal.

[44]  Kazuyuki Aihara,et al.  Graph distance for complex networks , 2016, Scientific Reports.

[45]  Danai Koutra,et al.  DeltaCon: Principled Massive-Graph Similarity Function with Attribution , 2016, ACM Trans. Knowl. Discov. Data.

[46]  Mehdi Layeghifard,et al.  Disentangling Interactions in the Microbiome: A Network Perspective , 2016, Trends in Microbiology.

[47]  Jure Leskovec,et al.  Spectral Graph Wavelets for Structural Role Similarity in Networks , 2017, ArXiv.

[48]  François G. Meyer,et al.  The Resistance Perturbation Distance: A Metric for the Analysis of Dynamic Networks , 2016, Discret. Appl. Math..