Predicting partially observed processes on temporal networks by Dynamics-Aware Node Embeddings (DyANE)

Koya Sato, Mizuki Oka, Alain Barrat, Ciro Cattuto, Predicting partially observed processes on temporal networks by Dynamics-Aware Node Embeddings (DyANE), EPJ Data Science 10:22 (2021)

Low-dimensional vector representations of network nodes have proven successful to feed graph data to machine learning algorithms and to improve performance across diverse tasks. Most of the embedding techniques, however, have been developed with the goal of achieving dense, low-dimensional encoding of network structure and patterns. Here, we present a node embedding technique aimed at providing low-dimensional feature vectors that are informative of dynamical processes occurring over temporal networks – rather than of the network structure itself – with the goal of enabling prediction tasks related to the evolution and outcome of these processes. We achieve this by using a lossless modified supra-adjacency representation of temporal networks and building on standard embedding techniques for static graphs based on random walks. We show that the resulting embedding vectors are useful for prediction tasks related to paradigmatic dynamical processes, namely epidemic spreading over empirical temporal networks. In particular, we illustrate the performance of our approach for the prediction of nodes’ epidemic states in single instances of a spreading process. We show how framing this task as a supervised multi-label classification task on the embedding vectors allows us to estimate the temporal evolution of the entire system from a partial sampling of nodes at random times, with potential impact for nowcasting infectious disease dynamics.


URL: https://epjdatascience.springeropen.com/articles/10.1140/epjds/s13688-021-00277-8

PDF: https://epjdatascience.springeropen.com/track/pdf/10.1140/epjds/s13688-021-00277-8.pdf

BIBTEX:

@article{cite-key,
	author = {Sato, Koya and Oka, Mizuki and Barrat, Alain and Cattuto, Ciro},
	journal = {EPJ Data Science},
	number = {1},
	pages = {22},
	title = {Predicting partially observed processes on temporal networks by Dynamics-Aware Node Embeddings (DyANE)},
	volume = {10},
	year = {2021}}

PUBLICATIONS

Building surrogate temporal network data from observed backbones
Effect of manual and digital contact tracing on COVID-19 outbreaks: a study on empirical contact data
Predicting partially observed processes on temporal networks by Dynamics-Aware Node Embeddings (DyANE)
Digital proximity tracing on empirical contact networks for pandemic control
Span-core Decomposition for Temporal Networks: Algorithms and Applications
Relevance of temporal cores for epidemic spread in temporal networks
Measuring social networks in primates: wearable sensors versus direct observations
The effect of age, environment and management on social contact patterns in sheep
High-resolution contact networks of free-ranging domestic dogs Canis familiaris and implications for transmission of infection
Simplicial models of social contagion
Study design and protocol for investigating social network patterns in rural and urban schools and households in a coastal setting in Kenya using wearable proximity sensors
Wearable Proximity Sensors for Monitoring a Mass Casualty Incident Exercise: Feasibility Study
The structured backbone of temporal social ties
Mining (maximal) span-cores from temporal networks
Estimating the outcome of spreading processes on networks with incomplete information: A dimensionality reduction approach
Close encounters between infants and household members measured through wearable proximity sensors
Can co-location be used as a proxy for face-to-face contacts?
Effect of risk perception on epidemic spreading in temporal networks
Estimating the epidemic risk using non-uniformly sampled contact data
Robust modeling of human contact networks across different scales and proximity-sensing techniques
Finding Collaboration Partners in a Scientific Community: The Role of Cognitive Group Awareness, Career Level, and Disciplinary Background
Recalibrating disease parameters for increasing realism in modeling epidemics in closed settings
School closure policies at municipality level for mitigating influenza spread: a model-based evaluation
Contact diaries versus wearable proximity sensors in measuring contact patterns at a conference: method comparison and participants’ attitudes
Impact of spatially constrained sampling of temporal contact networks on the evaluation of the epidemic risk
How to Estimate Epidemic Risk from Incomplete Contact Diaries Data?
Quantifying social contacts in a household setting of rural Kenya using wearable proximity sensors
Epidemic risk from friendship network data: an equivalence with a non-uniform sampling of contact networks
Compensating for population sampling in simulations of epidemic spread on temporal contact networks
Enhancing the evaluation of pathogen transmission risk in a hospital by merging hand-hygiene compliance and contact data: a proof-of-concept study
Contact patterns in a high school: a comparison between data collected using wearable sensors, contact diaries and friendship surveys
Data on face-to-face contacts in an office building suggest a low-cost vaccination strategy based on community linkers
Is Web Content a Good Proxy for Real-Life Interaction? A Case Study Considering Online and Offline Interactions of Computer Scientists
Combining High-Resolution Contact Data with Virological Data to Investigate Influenza Transmission in a Tertiary Care Hospital
Mental health and social networks in early adolescence: A dynamic study of objectively-measured social interaction behaviors
Mitigation of infectious disease at school: targeted class closure vs school closure
How memory generates heterogeneous dynamics in temporal networks
Contact patterns among high school students
Detecting the Community Structure and Activity Patterns of Temporal Networks: A Non-Negative Tensor Factorization Approach
Measuring contact patterns with wearable sensors: methods, data characteristics and applications to data-driven simulations of infectious diseases
Bootstrapping under constraint for the assessment of group behavior in human contact networks
Immunization strategies for epidemic processes in time-varying contact networks
Activity clocks: spreading dynamics on temporal networks of human contact
Gender homophily from spatial behavior in a primary school: a sociometric study
Estimating Potential Infection Transmission Routes in Hospital Wards Using Wearable Proximity Sensors
Empirical temporal networks of face-to-face human interactions
New Insights and Methods for Predicting Face-To-Face Contacts
Time-varying Social Networks in a Graph Database – A Neo4j Use Case
Temporal networks of face-to-face human interactions
An infectious disease model on empirical networks of human contact: bridging the gap between dynamic network data and contact matrices
Fingerprinting temporal networks of close-range human proximity
Digital Epidemiology
Random Walks on Temporal Networks
The making of Sixty-Nine Days Of Close Encounters At The Science Gallery.
High-Resolution Measurements of Face-to-Face Contact Patterns in a Primary School.
Simulation of an SEIR Infectious Disease Model on the Dynamic Contact Network of Conference Attendees.
On the Dynamics of Human Proximity for Data Diffusion in Ad-Hoc Networks.
Close Encounters in a Pediatric Ward: Measuring Face-to-Face Proximity and Mixing Patterns with Wearable Sensors.
What’s in a Crowd? Analysis of Face-to-Face Behavioral Networks.
Wearable Sensor Networks for Measuring Face-to-Face Contact Patterns in Healthcare Settings.
Social Dynamics in Conferences: Analysis of Data from the Live Social Semantics Application.
Providing Enhanced Social Interaction Services for Industry Exhibitors at large Medical Conferences.
Dynamics of Person-to-Person Interactions from Distributed RFID Sensor Networks.
Semantics, Sensors, and the Social Web: The Live Social Semantics Experiments.
The Live Social Semantics Application: a Platform for Integrating Face-to-Face Presence with On-Line Social Networking
Live Social Semantics
High Resolution Dynamical Mapping of Social Interactions With Active RFID.