Corpus ID: 235458024

An Attract-Repel Decomposition of Undirected Networks

  title={An Attract-Repel Decomposition of Undirected Networks},
  author={Alexander Peysakhovich and L{\'e}on Bottou},
Dot product latent space embedding is a common form of representation learning in undirected graphs (e.g. social networks, co-occurrence networks). We show that such models have problems dealing with ‘intransitive’ situations where A is linked to B, B is linked to C but A is not linked to C. Such situations occur in social networks when opposites attract (heterophily) and in co-occurrence networks when there are substitute nodes (e.g. the presence of Pepsi or Coke, but rarely both, in otherwise… Expand

Figures and Tables from this paper


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. Expand
The impossibility of low-rank representations for triangle-rich complex networks
It is mathematically proved that low-dimensional embeddings cannot generate graphs with both low average degree and large clustering coefficients, and any embedding that can successfully create these two properties must have a rank that is nearly linear in the number of vertices. Expand
Statistical Inference on Random Dot Product Graphs: a Survey
This survey paper describes a comprehensive paradigm for statistical inference on random dot product graphs, a paradigm centered on spectral embeddings of adjacency and Laplacian matrices, and investigates several real-world applications, including community detection and classification in large social networks and the determination of functional and biologically relevant network properties from an exploratory data analysis of the Drosophila connectome. Expand
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. Expand
A Consistent Adjacency Spectral Embedding for Stochastic Blockmodel Graphs
It is proved that this method to estimate block membership of nodes in a random graph generated by a stochastic blockmodel is consistent for assigning nodes to blocks, as only a negligible number of nodes will be misassigned. Expand
PyTorch-BigGraph: A Large-scale Graph Embedding System
PyTorch-BigGraph (PBG), an embedding system that incorporates several modifications to traditional multi-relation embedding systems that allow it to scale to graphs with billions of nodes and trillions of edges, is presented. Expand
Local Higher-Order Graph Clustering
The Motif-based Approximate Personalized PageRank (MAPPR) algorithm is developed, a generalization of the conductance metric for network motifs that finds clusters containing a seed node with minimalmotif conductance, and a theory of node neighborhoods for finding sets that have small motif conductance. Expand
Random Dot Product Graph Models for Social Networks
This paper explores two generalizations of the random dot product graph model proposed by Kraetzl, Nickel and Scheinerman, and Tucker and considers the properties of clustering, diameter and degree distribution with respect to these models. Expand
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. Expand
Structural equivalence of individuals in social networks
The aim of this paper is to understand the interrelations among relations within concrete social groups. Social structure is sought, not ideal types, although the latter are relevant toExpand