Accelerated attributed network embedding
Xiao Huang,Jundong Li,Xia Hu +2 more
- pp 633-641
TLDR
An accelerated attributed network embedding algorithm AANE is proposed, which enables the joint learning process to be done in a distributed manner by decomposing the complex modeling and optimization into many sub-problems.Abstract:
Network embedding is to learn low-dimensional vector representations for nodes in a network. It has shown to be effective in a variety of tasks such as node classification and link prediction. While embedding algorithms on pure networks have been intensively studied, in many real-world applications, nodes are often accompanied with a rich set of attributes or features, aka attributed networks. It has been observed that network topological structure and node attributes are often strongly correlated with each other. Thus modeling and incorporating node attribute proximity into network embedding could be potentially helpful, though non-trivial, in learning better vector representations. Meanwhile, real-world networks often contain a large number of nodes and features, which put demands on the scalability of embedding algorithms. To bridge the gap, in this paper, we propose an accelerated attributed network embedding algorithm AANE, which enables the joint learning process to be done in a distributed manner by decomposing the complex modeling and optimization into many sub-problems. Experimental results on several real-world datasets demonstrate the effectiveness and efficiency of the proposed algorithm.read more
Citations
More filters
Journal ArticleDOI
A Survey on Network Embedding
TL;DR: Network embedding assigns nodes in a network to low-dimensional representations and effectively preserves the network structure as discussed by the authors, and a significant amount of progress has been made toward this emerging network analysis paradigm.
Journal ArticleDOI
Attributed Social Network Embedding
TL;DR: This paper proposes a generic Attributed Social Network Embedding framework (ASNE), which learns representations for social actors by preserving both the structural proximity and attribute proximity, and shows significant gains on the tasks of link prediction and node classification.
Posted Content
Multi-scale Attributed Node Embedding
TL;DR: It is proved theoretically that matrices of node-feature pointwise mutual information are implicitly factorized by the embeddings, and computationally efficient and outperform comparable models on social networks and web graphs.
Posted Content
DynGEM: Deep Embedding Method for Dynamic Graphs.
TL;DR: This work presents an efficient algorithm DynGEM, based on recent advances in deep autoencoders for graph embeddings, that can handle growing dynamic graphs, and has better running time than using static embedding methods on each snapshot of a dynamic graph.
Proceedings ArticleDOI
Deep Attributed Network Embedding
Hongchang Gao,Heng Huang +1 more
TL;DR: This paper proposes a novel deep attributed network embedding approach, which can capture the high non-linearity and preserve various proximities in both topological structure and node attributes, and a novel strategy is proposed to guarantee the learned node representation can encode the consistent and complementary information from the topological structures and nodes attributes.
References
More filters
Journal ArticleDOI
Regression Shrinkage and Selection via the Lasso
TL;DR: A new method for estimation in linear models called the lasso, which minimizes the residual sum of squares subject to the sum of the absolute value of the coefficients being less than a constant, is proposed.
Book
Principal Component Analysis
TL;DR: In this article, the authors present a graphical representation of data using Principal Component Analysis (PCA) for time series and other non-independent data, as well as a generalization and adaptation of principal component analysis.
Book
Distributed Optimization and Statistical Learning Via the Alternating Direction Method of Multipliers
TL;DR: It is argued that the alternating direction method of multipliers is well suited to distributed convex optimization, and in particular to large-scale problems arising in statistics, machine learning, and related areas.
Journal ArticleDOI
Birds of a Feather: Homophily in Social Networks
TL;DR: The homophily principle as mentioned in this paper states that similarity breeds connection, and that people's personal networks are homogeneous with regard to many sociodemographic, behavioral, and intrapersonal characteristics.
Reference EntryDOI
Principal Component Analysis
TL;DR: Principal component analysis (PCA) as discussed by the authors replaces the p original variables by a smaller number, q, of derived variables, the principal components, which are linear combinations of the original variables.