Graphlet-orbit Transitions (GoT): A fingerprint for temporal network comparison

Abstract

Given a set of temporal networks, from different domains and with different sizes, how can we compare them? Can we identify evolutionary patterns that are both (i) characteristic and (ii) meaningful? We address these challenges by introducing a novel temporal and topological network fingerprint named Graphlet-orbit Transitions (GoT). We demonstrate that GoT provides very rich and interpretable network characterizations. Our work puts forward an extension of graphlets and uses the notion of orbits to encapsulate the roles of nodes in each subgraph. We build a transition matrix that keeps track of the temporal trajectory of nodes in terms of their orbits, therefore describing their evolution. We also introduce a metric (OTA) to compare two networks when considering these matrices. Our experiments show that networks representing similar systems have characteristic orbit transitions. GoT correctly groups synthetic networks pertaining to well-known graph models more accurately than competing static and dynamic state-of-the-art approaches by over 30%. Furthermore, our tests on real-world networks show that GoT produces highly interpretable results, which we use to provide insight into characteristic orbit transitions.

Supervised prediction of aging-related genes from a context-specific protein interaction subnetwork

“…• GoT [25] is another dynamic extension of static graphlets. GoT of a node counts how many times the node's participation in one graphlet (e.g., a triangle) changes to its participation in another graphlet (e.g., a 3-node path, when an edge of a triangle "breaks") between every two consecutive time points, and for every pair of considered graphlets (i.e., their orbits).…”

The power of dynamic social networks to predict individuals’ mental health

“…Graphlets are subgraphs, i.e., Lego-like basic building blocks of complex networks. They are state-of-the-art features, especially in dynamic networks [5,22,33]. While these features were proposed by others [5,22,33], we are the first of all social-networks-to-health studies to use them, which further distinguishes our work from the related studies.…”

“…They are state-of-the-art features, especially in dynamic networks [5,22,33]. While these features were proposed by others [5,22,33], we are the first of all social-networks-to-health studies to use them, which further distinguishes our work from the related studies. Note that this existing study [26] was just published, and we became aware of it after we completed all of our analyses and as we were finalizing our paper.…”

“…This is a typical strategy in many tasks and domains [14,31] and is thus not unique to this existing study [26]. In our study, on top of also using node centralities, we consider additional and possibly more powerful node features that are based on graphlets [5,22,33]. Graphlets are subgraphs, i.e., Lego-like basic building blocks of complex networks.…”

“…So, third, we develop a predictive model of mental health using three features of individuals extracted from the dynamic network: centralities in the dynamic network, dynamic graphlet degree vectors (dynamic GDV) [22], and graphlet orbit transitions (GoT) [5]. To evaluate the predictive power of these features, as a proof-of-concept, we train a logistic regression classifier for each feature to predict individuals as depressed or non-depressed (anxious or non-anxious).…”