Network Shrinkage Estimation

08/02/2019
by   Nesreen K. Ahmed, et al.
3

Networks are a natural representation of complex systems across the sciences, and higher-order dependencies are central to the understanding and modeling of these systems. However, in many practical applications such as online social networks, networks are massive, dynamic, and naturally streaming, where pairwise interactions become available one at a time in some arbitrary order. The massive size and streaming nature of these networks allow only partial observation, since it is infeasible to analyze the entire network. Under such scenarios, it is challenging to study the higher-order structural and connectivity patterns of streaming networks. In this work, we consider the fundamental problem of estimating the higher-order dependencies using adaptive sampling. We propose a novel adaptive, single-pass sampling framework and unbiased estimators for higher-order network analysis of large streaming networks. Our algorithms exploit adaptive techniques to identify edges that are highly informative for efficiently estimating the higher-order structure of streaming networks from small sample data. We also introduce a novel James-Stein-type shrinkage estimator to minimize the estimation error. Our approach is fully analytic with theoretical guarantees, computationally efficient, and can be incrementally updated in a streaming setting. Numerical experiments on large networks show that our approach is superior to baseline methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/19/2018

Tools for higher-order network analysis

Networks are a fundamental model of complex systems throughout the scien...
research
02/06/2021

Understanding Higher-order Structures in Evolving Graphs: A Simplicial Complex based Kernel Estimation Approach

Dynamic graphs are rife with higher-order interactions, such as co-autho...
research
03/15/2012

Approximating Higher-Order Distances Using Random Projections

We provide a simple method and relevant theoretical analysis for efficie...
research
06/11/2022

Sampling-based Estimation of the Number of Distinct Values in Distributed Environment

In data mining, estimating the number of distinct values (NDV) is a fund...
research
11/28/2018

Higher-Order Clustering in Heterogeneous Information Networks

As one type of complex networks widely-seen in real-world application, h...
research
11/14/2012

Network Sampling: From Static to Streaming Graphs

Network sampling is integral to the analysis of social, information, and...
research
05/18/2021

Nonparametric Modeling of Higher-Order Interactions via Hypergraphons

We study statistical and algorithmic aspects of using hypergraphons, tha...

Please sign up or login with your details

Forgot password? Click here to reset