SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning

05/08/2023
by   Junran Wu, et al.
0

In contrastive learning, the choice of “view” controls the information that the representation captures and influences the performance of the model. However, leading graph contrastive learning methods generally produce views via random corruption or learning, which could lead to the loss of essential information and alteration of semantic information. An anchor view that maintains the essential information of input graphs for contrastive learning has been hardly investigated. In this paper, based on the theory of graph information bottleneck, we deduce the definition of this anchor view; put differently, the anchor view with essential information of input graph is supposed to have the minimal structural uncertainty. Furthermore, guided by structural entropy, we implement the anchor view, termed SEGA, for graph contrastive learning. We extensively validate the proposed anchor view on various benchmarks regarding graph classification under unsupervised, semi-supervised, and transfer learning and achieve significant performance boosts compared to the state-of-the-art methods.

READ FULL TEXT

page 2

page 8

page 12

research
06/16/2022

Let Invariant Rationale Discovery Inspire Graph Contrastive Learning

Leading graph contrastive learning (GCL) methods perform graph augmentat...
research
03/24/2022

GraphCoCo: Graph Complementary Contrastive Learning

Graph Contrastive Learning (GCL) has shown promising performance in grap...
research
06/02/2022

Hard Negative Sampling Strategies for Contrastive Representation Learning

One of the challenges in contrastive learning is the selection of approp...
research
05/27/2023

GIMM: InfoMin-Max for Automated Graph Contrastive Learning

Graph contrastive learning (GCL) shows great potential in unsupervised g...
research
09/21/2021

AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators

Contrastive learning has been widely applied to graph representation lea...
research
10/28/2021

InfoGCL: Information-Aware Graph Contrastive Learning

Various graph contrastive learning models have been proposed to improve ...
research
04/17/2022

Global-Supervised Contrastive Loss and View-Aware-Based Post-Processing for Vehicle Re-Identification

In this paper, we propose a Global-Supervised Contrastive loss and a vie...

Please sign up or login with your details

Forgot password? Click here to reset