A Self-supervised Mixed-curvature Graph Neural Network

by   Li Sun, et al.
Beijing University of Posts and Telecommunications
Beihang University
North China Electric Power University
University of Illinois at Chicago

Graph representation learning received increasing attentions in recent years. Most of existing methods ignore the complexity of the graph structures and restrict graphs in a single constant-curvature representation space, which is only suitable to particular kinds of graph structure indeed. Additionally, these methods follow the supervised or semi-supervised learning paradigm, and thereby notably limit their deployment on the unlabeled graphs in real applications. To address these aforementioned limitations, we take the first attempt to study the self-supervised graph representation learning in the mixed-curvature spaces. In this paper, we present a novel Self-supervised Mixed-curvature Graph Neural Network (SelfMGNN). Instead of working on one single constant-curvature space, we construct a mixed-curvature space via the Cartesian product of multiple Riemannian component spaces and design hierarchical attention mechanisms for learning and fusing the representations across these component spaces. To enable the self-supervisd learning, we propose a novel dual contrastive approach. The mixed-curvature Riemannian space actually provides multiple Riemannian views for the contrastive learning. We introduce a Riemannian projector to reveal these views, and utilize a well-designed Riemannian discriminator for the single-view and cross-view contrastive learning within and across the Riemannian views. Finally, extensive experiments show that SelfMGNN captures the complicated graph structures in reality and outperforms state-of-the-art baselines.


page 1

page 2

page 3

page 4


A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning

Representation learning on temporal graphs has drawn considerable resear...

Contrastive Graph Clustering in Curvature Spaces

Graph clustering is a longstanding research topic, and has achieved rema...

Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces

Continual graph learning routinely finds its role in a variety of real-w...

Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning

Heterogeneous graph neural network (HGNN) is a very popular technique fo...

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

Self-supervised learning is gaining considerable attention as a solution...

Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming

Graph representation learning (GRL) is critical for graph-structured dat...

Projections of Model Spaces for Latent Graph Inference

Graph Neural Networks leverage the connectivity structure of graphs as a...

Please sign up or login with your details

Forgot password? Click here to reset