Tracking Switched Dynamic Network Topologies from Information Cascades

Abstract

Contagions such as the spread of popular news stories, or infectious diseases, propagate in cascades over dynamic networks with unobservable topologies. However, "social signals" such as product purchase time, or blog entry timestamps are measurable, and implicitly depend on the underlying topology, making it possible to track it over time. Interestingly, network topologies often "jump" between discrete states that may account for sudden changes in the observed signals. The present paper advocates a switched dynamic structural equation model to capture the topology-dependent cascade evolution, as well as the discrete states driving the underlying topologies. Conditions under which the proposed switched model is identifiable are established. Leveraging the edge sparsity inherent to social networks, a recursive ${\ell }_1$-norm regularized least-squares estimator is put forth to jointly track the states and network topologies. An efficient first-order proximal-gradient algorithm is developed to solve the resulting optimization problem. Numerical experiments on both synthetic data and real cascades measured over the span of one year are conducted, and test results corroborate the efficacy of the advocated approach.

References in corpus (4)

• Kronecker Graphs: An Approach to Modeling Networks
• Uncovering the Temporal Dynamics of Diffusion Networks
• On the Convexity of Latent Social Network Inference
• Network Granger Causality with Inherent Grouping Structure

Cited by in corpus (8)

• Learning graphs from data: A signal representation perspective
• Graph Representation Learning: A Survey
• Joint Inference of Multiple Graphs from Matrix Polynomials
• Graph Learning for Spatiotemporal Signals with Long- and Short-Term Characterization
• Online Inference for Mixture Model of Streaming Graph Signals with Non-White Excitation
• A Hierarchical Graph Signal Processing Approach to Inference from Spatiotemporal Signals
• Dynamic network identification from non-stationary vector autoregressive time series
• Joint Network Topology Inference via Structured Fusion Regularization