Conditional Distribution Learning for Graph Classification

TL;DR

This paper introduces a conditional distribution learning approach for graph classification that aligns augmented feature distributions to preserve semantic information and mitigates conflicts between message passing and contrastive learning.

Contribution

It proposes an end-to-end graph representation model that aligns distributions of augmented features, effectively balancing message passing and contrastive learning.

Findings

Improves graph classification accuracy on benchmark datasets.

Effectively preserves semantic information during augmentation.

Balances message passing with contrastive learning.

Abstract

Leveraging the diversity and quantity of data provided by various graph-structured data augmentations while preserving intrinsic semantic information is challenging. Additionally, successive layers in graph neural network (GNN) tend to produce more similar node embeddings, while graph contrastive learning aims to increase the dissimilarity between negative pairs of node embeddings. This inevitably results in a conflict between the message-passing mechanism (MPM) of GNNs and the contrastive learning (CL) of negative pairs via intraviews. In this paper, we propose a conditional distribution learning (CDL) method that learns graph representations from graph-structured data for semisupervised graph classification. Specifically, we present an end-to-end graph representation learning model to align the conditional distributions of weakly and strongly augmented features over the original features. This alignment enables the CDL model to effectively preserve intrinsic semantic information when both weak and strong augmentations are applied to graph-structured data. To avoid the conflict between the MPM and the CL of negative pairs, positive pairs of node representations are retained for measuring the similarity between the original features and the corresponding weakly augmented features. Extensive experiments with several benchmark graph datasets demonstrate the effectiveness of the proposed CDL method.