Computing Network Centrality Measures using Neural Networks

Slides:



Advertisements
Similar presentations
Introduction to Graph Theory Instructor: Dr. Chaudhary Department of Computer Science Millersville University Reading Assignment Chapter 1.
Advertisements

Analysis and Modeling of Social Networks Foudalis Ilias.
It’s a Small World by Jamie Luo. Introduction Small World Networks and their place in Network Theory An application of a 1D small world network to model.
Hierarchical Decompositions for Congestion Minimization in Networks Harald Räcke 1.
A Probabilistic Model for Road Selection in Mobile Maps Thomas C. van Dijk Jan-Henrik Haunert W2GIS, 5 April 2013.
1 Mazes In The Theory of Computer Science Dana Moshkovitz.
Centrality Measures These measure a nodes importance or prominence in the network. The more central a node is in a network the more significant it is to.
How is this going to make us 100K Applications of Graph Theory.
Hazırlayan NEURAL NETWORKS Radial Basis Function Networks I PROF. DR. YUSUF OYSAL.
Hazırlayan NEURAL NETWORKS Radial Basis Function Networks II PROF. DR. YUSUF OYSAL.
Network Measures Social Media Mining. 2 Measures and Metrics 2 Social Media Mining Network Measures Klout.
Google’s PageRank: The Math Behind the Search Engine Author:Rebecca S. Wills, 2006 Instructor: Dr. Yuan Presenter: Wayne.
An Illustration of Prim's Algorithm
Presentation on Neural Networks.. Basics Of Neural Networks Neural networks refers to a connectionist model that simulates the biophysical information.
Distributed Computing Rik Sarkar. Distributed Computing Old style: Use a computer for computation.
COM1721: Freshman Honors Seminar A Random Walk Through Computing Lecture 2: Structure of the Web October 1, 2002.
Centrality Spring 2012.
Presentation: A measure of betweenness centrality based on random walks M.E.J. Newman ELSEVIER Social Networks November 2004 A measure of betweenness centrality.
The new protocol of freenet Taken from Ian Clarke and Oskar Sandberg (The Freenet Project)
Information Retrieval and Web Search Link analysis Instructor: Rada Mihalcea (Note: This slide set was adapted from an IR course taught by Prof. Chris.
1 Friends and Neighbors on the Web Presentation for Web Information Retrieval Bruno Lepri.
CS 590 Term Project Epidemic model on Facebook
Community detection via random walk Draft slides.
An Improved Acquaintance Immunization Strategy for Complex Network.
“Important” Vertices and the PageRank Algorithm Networked Life NETS 112 Fall 2014 Prof. Michael Kearns.
Google’s means to provide better search results Qi-Yuan Gou.
Dynamic Network Analysis Case study of PageRank-based Rewiring Narjès Bellamine-BenSaoud Galen Wilkerson 2 nd Second Annual French Complex Systems Summer.
Topics In Social Computing (67810) Module 1 (Structure) Centrality Measures, Graph Clustering Random Walks on Graphs.
CRIM6660 Terrorist Networks Lesson 1: Introduction, Terms and Definitions.
Cmpe 588- Modeling of Internet Emergence of Scale-Free Network with Chaotic Units Pulin Gong, Cees van Leeuwen by Oya Ünlü Instructor: Haluk Bingöl.
Self-Organizing Network Model (SOM) Session 11
Convolutional Neural Network
Deep Feedforward Networks
Through University Faculty
Sofus A. Macskassy Fetch Technologies
DTMC Applications Ranking Web Pages & Slotted ALOHA
Neural Networks Dr. Peter Phillips.
Node Similarity Ralucca Gera,
Degree and Eigenvector Centrality
Section 7.12: Similarity By: Ralucca Gera, NPS.
Centrality in Social Networks
Prof. Paolo Ferragina, Algoritmi per "Information Retrieval"
Closeness Centrality.
PageRank algorithm based on Eigenvectors
Prof. Paolo Ferragina, Algoritmi per "Information Retrieval"
Closeness Centrality.
Noémi Gaskó, Rodica Ioana Lung, Mihai Alexandru Suciu
Word Embedding Word2Vec.
Katz Centrality (directed graphs).
The use of Neural Networks to schedule flow-shop with dynamic job arrival ‘A Multi-Neural Network Learning for lot Sizing and Sequencing on a Flow-Shop’
Capabilities of Threshold Neurons
ML – Lecture 3B Deep NN.
Section 8.3: Degree Distribution
Properties and applications of spectra for networks
Overview of deep learning
Word2Vec.
Computer Vision Lecture 19: Object Recognition III
Algorithms Lecture # 27 Dr. Sohail Aslam.
Warm Up – Tuesday Find the critical times for each vertex.
Degree Distribution Ralucca Gera,
Machine Learning – a Probabilistic Perspective
Randomized Algorithms
Navigation and Propagation in Networks
DATA-Intensive systems Department of computer science
Keshav Balasubramanian
Randomized Algorithms
Sequences II Prof. Noah Snavely CS1114
Heterogeneous Graph Convolutional Network
2019/9/14 The Deep Learning Vision for Heterogeneous Network Traffic Control Proposal, Challenges, and Future Perspective Author: Nei Kato, Zubair Md.
Learning to Cluster Faces on an Affinity Graph
Presentation transcript:

Computing Network Centrality Measures using Neural Networks Dvir Cohen, Matan Hugi, Zion Sofer Advisors: Prof. Aryeh Kontorovich, Dr. Rami Puzis, Prof. Lior Rokach

Introduction Our goal is to compute node centrality in graphs using Neural Networks. Our course of action was building a neural network that computes node centrality using vertex embedding methods. The neural network computed the centrality without any external supervision or direction.

Motivation In graph theory and network analysis, indicators of centrality identify the most important vertices within a graph. Applications include: Finding the most influential person(s) in a social network. PageRank – Google’s method for deciding which page is displayed first. Key infrastructure nodes in the internet or urban networks. Super spreaders of disease. Predicting signaling behaviors in bottlenose dolphin groups.

Centrality Measures Which one is the most important one? Centrality measures is a way to determine which nodes in the graph is the most “important”. There are several deterministic centrality measures including Degree Centrality, Eigenvector Centrality, Closeness Centrality and Betweenness Centrality. Which one is the most important one?

Centrality Measures limitations One of the reasons why so many centrality measures have been defined is because all of the measures have limitations. For example: in a simple analysis of who's most popular in a social network, prioritizing nodes by betweenness centrality could be misleading. Meanwhile, a lot of immunization strategies in analyses of epidemic spreading rely on immunizing nodes with high betweenness. In this circumstance, immunizing people based on their degree centrality could be sub-optimal.

Random Walks 𝑊={′5′, ′2′, ′1′, ′5′, ′4′} A random walk is a finite series of connected vertices in a graph, chosen randomly at each point in the walk. To generate a random walk from a certain vertex, we simply choose one of the neighbors of the vertex at random (If available) and continue from the chosen vertex in the same manner. For example, a random walk of length 4 from vertex “5” for the following graph could be 𝑊={′5′, ′2′, ′1′, ′5′, ′4′}

word2vec Word2vec is a group of related models that are used to produce word embeddings. These models are shallow, two-layer neural networks that are trained to reconstruct linguistic contexts of words. And so, the linear combination [king] – [man] + [woman] Will be equal (In high probability) to [queen]

Algorithm Flow Graph Random walks word2vec Centrality

Training the word2vec network ['Node0 Node8 Node4 Node8 Node0 Node8‘] ['Node0 Node8 Node9 Node6 Node5 Node9'] ['Node3 Node7 Node3 Node7 Node9 Node5'] ['Node6 Node9 Node8 Node9 Node7 Node5'] ['Node9 Node7 Node5 Node6 Node5 Node7']

Learning the centrality of the nodes 0.106 0.025 0.026 0.076 0.083 0.090 0.080 0.154 0.164 0.192

Results We computed the correlation between the output vector generated from our algorithm with popular closeness measures computed on the same graph Name Pearson Spearman linregress correlation p-value DMZ centrality 1 closeness centrality 0.8798 0.0007 0.9224 0.0001 0.774 0.3082 betweenness centrality 0.8443 0.0021 0.8739 0.0009 0.7129 0.0943 eigenvector centrality 0.715 0.02 0.8292 0.003 0.5113 0.2527 degree centrality 0.7072 0.0221 0.7236 0.0179 0.5001 0.3195

Conclusion ניתן לראות מהנתונים כי המידע עקבי והגיוני לאורך הניסוי, על סוגים שונים של גרפים. התחום של עבודה עם גרפים ורשתות נוירונים הינו תחום יחסית בחיתוליו ואנו מקווים שהפרויקט שלנו יוכל לתרום לקידום התחום. (להגיד אולי אם יוצא מאמר – לדבר עם רמי לפני) לראיה, בעת שהיינו בלב הפרויקט, יצא מאמר לפני כ – 3 חודשים בשם node2vec אשר משתמש במתודולוגיה הדומה לשלנו, אם כי למטרה שונה לחלוטין.