Heterogeneous Graph Sparsification for Efficient Representation Learning

11/14/2022
by   Chandan Chunduru, et al.
0

Graph sparsification is a powerful tool to approximate an arbitrary graph and has been used in machine learning over homogeneous graphs. In heterogeneous graphs such as knowledge graphs, however, sparsification has not been systematically exploited to improve efficiency of learning tasks. In this work, we initiate the study on heterogeneous graph sparsification and develop sampling-based algorithms for constructing sparsifiers that are provably sparse and preserve important information in the original graphs. We have performed extensive experiments to confirm that the proposed method can improve time and space complexities of representation learning while achieving comparable, or even better performance in subsequent graph learning tasks based on the learned embedding.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/07/2019

On the Interpretability and Evaluation of Graph Representation Learning

With the rising interest in graph representation learning, a variety of ...
research
04/25/2023

Connector 0.5: A unified framework for graph representation learning

Graph representation learning models aim to represent the graph structur...
research
09/25/2019

PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions

Graph node embedding aims at learning a vector representation for all no...
research
03/05/2022

Flurry: a Fast Framework for Reproducible Multi-layered Provenance Graph Representation Learning

Complex heterogeneous dynamic networks like knowledge graphs are powerfu...
research
01/24/2019

Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back

A graph is a powerful concept for representation of relations between pa...
research
07/31/2018

A First Experiment on Including Text Literals in KGloVe

Graph embedding models produce embedding vectors for entities and relati...
research
09/04/2020

About Graph Degeneracy, Representation Learning and Scalability

Graphs or networks are a very convenient way to represent data with lots...

Please sign up or login with your details

Forgot password? Click here to reset