Degree-Based Random Walk Approach for Graph Embedding

  title={Degree-Based Random Walk Approach for Graph Embedding},
  author={Sarmad N. Mohammed and Semra G{\"u}nd{\"u}ç},
Graph embedding, representing local and global neighbourhood information by numerical vectors, is a crucial part of the mathematical modeling of a wide range of real-world systems. Among the embedding algorithms, random walk-based algorithms have proven to be very successful. These algorithms collect information by creating numerous random walks with a predefined number of steps. Creating random walks is the most demanding part of the embedding process. The computation demand increases with the… 

Figures and Tables from this paper

The Influence of Network Structural Preference on Node Classification and Link Prediction

This work introduces a new feature abstraction method, namely the Transition Probabilities Matrix (TPM), based on embedding anonymous random walks on feature vectors, which is superior to the state-of-the-art algorithms in terms of cross-networks generalization tasks.



Degree-biased random walk for large-scale network embedding

BalNode2Vec: Balanced Random Walk based Versatile Feature Learning for Networks

This research proposes BalNode2Vec – a new sampling algorithm for learning feature representations for nodes in networks by using balanced random walks and defines a notion of a nodes network neighborhood and design a balanced random walk procedure, which adapts to the graph topology.

Random-Walk Computation of Similarities between Nodes of a Graph with Application to Collaborative Recommendation

The model, which nicely fits into the so-called "statistical relational learning" framework, could also be used to compute document or word similarities, and could be applied to machine-learning and pattern-recognition tasks involving a relational database.

LINE: Large-scale Information Network Embedding

A novel network embedding method called the ``LINE,'' which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted, and optimizes a carefully designed objective function that preserves both the local and global network structures.

Method to find community structures based on information centrality.

An algorithm of hierarchical clustering that consists in finding and removing iteratively the edge with the highest information centrality is developed that is very effective especially when the communities are very mixed and hardly detectable by the other methods.

Local Graph Partitioning using PageRank Vectors

An improved algorithm for computing approximate PageRank vectors, which allows us to find a cut with conductance at most oslash and approximately optimal balance in time O(m log4 m/oslash) in time proportional to its size.

BiasedWalk: Biased Sampling for Representation Learning on Graphs

Biased-Walk is proposed, a scalable, unsupervised feature learning algorithm that is based on biased random walks to sample context information about each node in the network, which outperforms the baseline ones in most of the tasks and datasets.

Community detection in graphs

Community structure in social and biological networks

  • M. GirvanM. Newman
  • Computer Science
    Proceedings of the National Academy of Sciences of the United States of America
  • 2002
This article proposes a method for detecting communities, built around the idea of using centrality indices to find community boundaries, and tests it on computer-generated and real-world graphs whose community structure is already known and finds that the method detects this known structure with high sensitivity and reliability.

Exploring Network Structure, Dynamics, and Function using NetworkX

Some of the recent work studying synchronization of coupled oscillators is discussed to demonstrate how NetworkX enables research in the field of computational networks.