motif2vec: Motif Aware Node Representation Learning for Heterogeneous Networks

08/22/2019
by   Manoj Reddy Dareddy, et al.
0

Recent years have witnessed a surge of interest in machine learning on graphs and networks with applications ranging from vehicular network design to IoT traffic management to social network recommendations. Supervised machine learning tasks in networks such as node classification and link prediction require us to perform feature engineering that is known and agreed to be the key to success in applied machine learning. Research efforts dedicated to representation learning, especially representation learning using deep learning, has shown us ways to automatically learn relevant features from vast amounts of potentially noisy, raw data. However, most of the methods are not adequate to handle heterogeneous information networks which pretty much represents most real-world data today. The methods cannot preserve the structure and semantic of multiple types of nodes and links well enough, capture higher-order heterogeneous connectivity patterns, and ensure coverage of nodes for which representations are generated. We propose a novel efficient algorithm, motif2vec that learns node representations or embeddings for heterogeneous networks. Specifically, we leverage higher-order, recurring, and statistically significant network connectivity patterns in the form of motifs to transform the original graph to motif graph(s), conduct biased random walk to efficiently explore higher order neighborhoods, and then employ heterogeneous skip-gram model to generate the embeddings. Unlike previous efforts that uses different graph meta-structures to guide the random walk, we use graph motifs to transform the original network and preserve the heterogeneity. We evaluate the proposed algorithm on multiple real-world networks from diverse domains and against existing state-of-the-art methods on multi-class node classification and link prediction tasks, and demonstrate its consistent superiority over prior work.

READ FULL TEXT
research
07/03/2016

node2vec: Scalable Feature Learning for Networks

Prediction tasks over nodes and edges in networks require careful effort...
research
11/20/2019

Exponential Family Graph Embeddings

Representing networks in a low dimensional latent space is a crucial tas...
research
01/02/2021

Representation Learning of Reconstructed Graphs Using Random Walk Graph Convolutional Network

Graphs are often used to organize data because of their simple topologic...
research
08/15/2019

HONEM: Network Embedding Using Higher-Order Patterns in Sequential Data

Representation learning offers a powerful alternative to the oft painsta...
research
05/16/2017

Learning Edge Representations via Low-Rank Asymmetric Projections

We propose a new method for embedding graphs while preserving directed e...
research
01/30/2023

Lateralized Learning for Multi-Class Visual Classification Tasks

The majority of computer vision algorithms fail to find higher-order (ab...
research
04/29/2021

Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning

Graph representation learning has become a ubiquitous component in many ...

Please sign up or login with your details

Forgot password? Click here to reset