Self-Supervised Graph Representation Learning via Global Context Prediction

03/03/2020
by   Zhen Peng, et al.
0

To take full advantage of fast-growing unlabeled networked data, this paper introduces a novel self-supervised strategy for graph representation learning by exploiting natural supervision provided by the data itself. Inspired by human social behavior, we assume that the global context of each node is composed of all nodes in the graph since two arbitrary entities in a connected network could interact with each other via paths of varying length. Based on this, we investigate whether the global context can be a source of free and effective supervisory signals for learning useful node representations. Specifically, we randomly select pairs of nodes in a graph and train a well-designed neural net to predict the contextual position of one node relative to the other. Our underlying hypothesis is that the representations learned from such within-graph context would capture the global topology of the graph and finely characterize the similarity and differentiation between nodes, which is conducive to various downstream learning tasks. Extensive benchmark experiments including node classification, clustering, and link prediction demonstrate that our approach outperforms many state-of-the-art unsupervised methods and sometimes even exceeds the performance of supervised counterparts.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/15/2020

Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning

Unsupervised (or self-supervised) graph representation learning is essen...
research
07/22/2020

Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networks

Representation learning methods for heterogeneous networks produce a low...
research
02/09/2023

Self-Supervised Node Representation Learning via Node-to-Neighbourhood Alignment

Self-supervised node representation learning aims to learn node represen...
research
10/25/2022

LaundroGraph: Self-Supervised Graph Representation Learning for Anti-Money Laundering

Anti-money laundering (AML) regulations mandate financial institutions t...
research
05/31/2022

Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning

Unsupervised/self-supervised graph representation learning is critical f...
research
04/24/2014

Classifying pairs with trees for supervised biological network inference

Networks are ubiquitous in biology and computational approaches have bee...
research
03/03/2022

Graph Representation Learning Beyond Node and Homophily

Unsupervised graph representation learning aims to distill various graph...

Please sign up or login with your details

Forgot password? Click here to reset