Scalable Graph Embeddings via Sparse Transpose Proximities

05/16/2019
by   Zhewei Wei, et al.
0

Graph embedding learns low-dimensional representations for nodes in a graph and effectively preserves the graph structure. Recently, a significant amount of progress has been made toward this emerging research area. However, there are several fundamental problems that remain open. First, existing methods fail to preserve the out-degree distributions on directed graphs. Second, many existing methods employ random walk based proximities and thus suffer from conflicting optimization goals on undirected graphs. Finally, existing factorization methods are unable to achieve scalability and non-linearity simultaneously. This paper presents an in-depth study on graph embedding techniques on both directed and undirected graphs. We analyze the fundamental reasons that lead to the distortion of out-degree distributions and to the conflicting optimization goals. We propose transpose proximity, a unified approach that solves both problems. Based on the concept of transpose proximity, we design , a factorization based graph embedding algorithm that achieves scalability and non-linearity simultaneously. makes use of the backward push algorithm to efficiently compute the sparse Personalized PageRank (PPR) as its transpose proximities. By imposing the sparsity constraint, we are able to apply non-linear operations to the proximity matrix and perform efficient matrix factorization to derive the embedding vectors. Finally, we present an extensive experimental study that evaluates the effectiveness of various graph embedding algorithms, and we show that outperforms the state-of-the-art methods in terms of effectiveness and scalability.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/10/2021

Learning Based Proximity Matrix Factorization for Node Embedding

Node embedding learns a low-dimensional representation for each node in ...
research
11/11/2017

Generalized Neural Graph Embedding with Matrix Factorization

Recent advances in language modeling such as word2vec motivate a number ...
research
11/18/2019

RWNE: A Scalable Random-Walk based Network Embedding Framework with Personalized Higher-order Proximity Preserved

Higher-order proximity preserved network embedding has attracted increas...
research
02/19/2014

Transduction on Directed Graphs via Absorbing Random Walks

In this paper we consider the problem of graph-based transductive classi...
research
03/28/2023

Distributed Graph Embedding with Information-Oriented Random Walks

Graph embedding maps graph nodes to low-dimensional vectors, and is wide...
research
06/03/2023

Accelerating Personalized PageRank Vector Computation

Personalized PageRank Vectors are widely used as fundamental graph-learn...
research
11/14/2018

SepNE: Bringing Separability to Network Embedding

Many successful methods have been proposed for learning low dimensional ...

Please sign up or login with your details

Forgot password? Click here to reset