DeepAI
Log In Sign Up

Multi-scale Attributed Node Embedding

09/28/2019
by   Benedek Rozemberczki, et al.
0

We present network embedding algorithms that capture information about a node from the local distribution over node attributes around it, as observed over random walks following an approach similar to Skip-gram. Observations from neighborhoods of different sizes are either pooled (AE) or encoded distinctly in a multi-scale approach (MUSAE). Capturing attribute-neighborhood relationships over multiple scales is useful for a diverse range of applications, including latent feature identification across disconnected networks with similar attributes. We prove theoretically that matrices of node-feature pointwise mutual information are implicitly factorized by the embeddings. Experiments show that our algorithms are robust, computationally efficient and outperform comparable models on social, web and citation network datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/17/2021

CoANE: Modeling Context Co-occurrence for Attributed Network Embedding

Attributed network embedding (ANE) is to learn low-dimensional vectors s...
11/28/2018

Attributed Network Embedding for Incomplete Structure Information

An attributed network enriches a pure network by encoding a part of wide...
11/03/2020

GAGE: Geometry Preserving Attributed Graph Embeddings

Node representation learning is the task of extracting concise and infor...
04/15/2021

Variational Co-embedding Learning for Attributed Network Clustering

Recent works for attributed network clustering utilize graph convolution...
10/31/2019

Semi-supervisedly Co-embedding Attributed Networks

Deep generative models (DGMs) have achieved remarkable advances. Semi-su...
09/01/2015

Iterative hypothesis testing for multi-object tracking in presence of features with variable reliability

This paper assumes prior detections of multiple targets at each time ins...
06/02/2022

Graph Kernels Based on Multi-scale Graph Embeddings

Graph kernels are conventional methods for computing graph similarities....

Code Repositories

MUSAE

The reference implementation of "Multi-scale Attributed Node Embedding".


view repo