Geometry Contrastive Learning on Heterogeneous Graphs

06/25/2022
by   Shichao Zhu, et al.
0

Self-supervised learning (especially contrastive learning) methods on heterogeneous graphs can effectively get rid of the dependence on supervisory data. Meanwhile, most existing representation learning methods embed the heterogeneous graphs into a single geometric space, either Euclidean or hyperbolic. This kind of single geometric view is usually not enough to observe the complete picture of heterogeneous graphs due to their rich semantics and complex structures. Under these observations, this paper proposes a novel self-supervised learning method, termed as Geometry Contrastive Learning (GCL), to better represent the heterogeneous graphs when supervisory data is unavailable. GCL views a heterogeneous graph from Euclidean and hyperbolic perspective simultaneously, aiming to make a strong merger of the ability of modeling rich semantics and complex structures, which is expected to bring in more benefits for downstream tasks. GCL maximizes the mutual information between two geometric views by contrasting representations at both local-local and local-global semantic levels. Extensive experiments on four benchmarks data sets show that the proposed approach outperforms the strong baselines, including both unsupervised methods and supervised methods, on three tasks, including node classification, node clustering and similarity search.

READ FULL TEXT
research
02/02/2023

Hyperbolic Contrastive Learning

Learning good image representations that are beneficial to downstream ta...
research
10/12/2019

Neighborhood Growth Determines Geometric Priors for Relational Representation Learning

The problem of identifying geometric structure in heterogeneous, high-di...
research
03/15/2023

RGI : Regularized Graph Infomax for self-supervised learning on graphs

Self-supervised learning is gaining considerable attention as a solution...
research
04/30/2022

Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning

Heterogeneous graph neural network (HGNN) is a very popular technique fo...
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
05/18/2023

HMSN: Hyperbolic Self-Supervised Learning by Clustering with Ideal Prototypes

Hyperbolic manifolds for visual representation learning allow for effect...
research
06/12/2023

CARL-G: Clustering-Accelerated Representation Learning on Graphs

Self-supervised learning on graphs has made large strides in achieving g...

Please sign up or login with your details

Forgot password? Click here to reset