Representation Learning for Scale-free Networks

  title={Representation Learning for Scale-free Networks},
  author={Rui Feng and Yang Yang and Wenjie Hu and Fei Wu and Yueting Zhuang},
Network embedding aims to learn the low-dimensional representations of vertexes in a network, while structure and inherent properties of the network is preserved. Existing network embedding works primarily focus on preserving the microscopic structure, such as the first- and second-order proximity of vertexes, while the macroscopic scale-free property is largely ignored. Scale-free property depicts the fact that vertex degrees follow a heavy-tailed distribution (i.e., only a few vertexes… 

Figures and Tables from this paper

FLGAI: a unified network embedding framework integrating multi-scale network structures and node attribute information
A novel nonnegative matrix factorization (NMF) based network representation learning framework called FLGAI is proposed, which jointly integrates the local network structure, globalnetwork structure, and attribute information to learn the network representation.
Network2Vec: Learning Node Representation Based on Space Mapping in Networks
This work proposes a lightweight model, entitled Network2Vec, to learn network embedding on the base of semantic distance mapping between the graph space and embedding space, which builds a bridge between the two spaces leveraging the property of group homomorphism.
DDNE: Discriminative Distance Metric Learning for Network Embedding
A unified framework to encode distributional similarity and measure adjacency similarity simultaneously simultaneously, named DDNE is proposed, which trains a siamese neural network which learns a set of non-linear transforms to project the node pairs into the same low-dimensional space based on their first-order proximity.
Bringing Order to Network Embedding: A Relative Ranking based Approach
The key idea is to decompose the overall objective function into the summation of a goodness function over a set of edges to collectively preserve their relative rankings on the context network.
Nonuniform Hyper-Network Embedding with Dual Mechanism
This article proposes a flexible model called Hyper2vec and combines the features of hyperedges by considering the dual hyper-networks to build a further model called NHNE based on 1D convolutional neural networks, and train a tuplewise similarity function for the nonuniform relationships in hyper-nets.
SPINE: Structural Identity Preserved Inductive Network Embedding
This paper presents SPINE, a method that can jointly capture the local proximity and proximities at any distance, while being inductive to efficiently deal with unseen nodes or networks.
How much topological structure is preserved by graph embeddings?
It is found that it is insufficient to rely on the embeddings to reconstruct the original graph, to discover communities, and to predict links at a high precision, so the embeds by the state-of-the-art approaches can only preserve part of the topological structure.
Network representation learning: models, methods and applications
A taxonomy of network embedding methods based on the type of networks and review the major research works that come under each category is built and various directions for future work are provided which enhance further research.
Network Representation Learning: A Survey
A comprehensive review of the current literature on network representation learning in the data mining and machine learning field, proposing new taxonomies to categorize and summarize the state-of-the-art network representationLearning techniques according to the underlying learning mechanisms, the network information intended to preserve, as well as the algorithmic designs and methodologies.


Community Preserving Network Embedding
A novel Modularized Nonnegative Matrix Factorization (M-NMF) model is proposed to incorporate the community structure into network embedding and jointly optimize NMF based representation learning model and modularity based community detection model in a unified framework, which enables the learned representations of nodes to preserve both of the microscopic and community structures.
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.
Structure preserving embedding
SPE provides significant improvements in terms of visualization and lossless compression of graphs, outperforming popular methods such as spectral embedding and Laplacian eigen-maps and introducing structure preserving constraints into dimensionality reduction algorithms produces more accurate representations of high-dimensional data.
node2vec: Scalable Feature Learning for Networks
In node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks, a flexible notion of a node's network neighborhood is defined and a biased random walk procedure is designed, which efficiently explores diverse neighborhoods.
Efficient embedding of complex networks to hyperbolic space via their Laplacian
The Laplacian-based Network Embedding is followed, a simple yet accurate, efficient and data driven manifold learning approach, which allows for the quick geometric analysis of big networks.
DeepWalk: online learning of social representations
DeepWalk is an online learning algorithm which builds useful incremental results, and is trivially parallelizable, which make it suitable for a broad class of real world applications such as network classification, and anomaly detection.
metapath2vec: Scalable Representation Learning for Heterogeneous Networks
Two scalable representation learning models, namely metapath2vec and metapATH2vec++, are developed that are able to not only outperform state-of-the-art embedding models in various heterogeneous network mining tasks, but also discern the structural and semantic correlations between diverse network objects.
Graph evolution: Densification and shrinking diameters
A new graph generator is provided, based on a forest fire spreading process that has a simple, intuitive justification, requires very few parameters, and produces graphs exhibiting the full range of properties observed both in prior work and in the present study.
Learning to Discover Social Circles in Ego Networks
A novel machine learning task of identifying users' social circles is defined as a node clustering problem on a user's ego-network, a network of connections between her friends, and a model for detecting circles is developed that combines network structure as well as user profile information.
Growing network with local rules: preferential attachment, clustering hierarchy, and degree correlations.
  • A. Vázquez
  • Computer Science
    Physical review. E, Statistical, nonlinear, and soft matter physics
  • 2003
It is claimed that an effective linear preferential attachment is the natural outcome of growing network models based on local rules and that the local models offer an explanation for other properties like the clustering hierarchy and degree correlations recently observed in complex networks.