Supervised Contrastive Learning with Structure Inference for Graph Classification

TL;DR

This paper introduces a novel graph neural network framework that combines supervised contrastive learning with structure inference to enhance graph classification by discovering additional connections and leveraging label information for more discriminative embeddings.

Contribution

The paper proposes a new graph neural network approach integrating structure inference via diffusion cascades and supervised contrastive loss to improve graph classification performance.

Findings

Outperforms recent state-of-the-art methods in graph classification tasks.

Effective structure inference enhances the quality of graph embeddings.

Supervised contrastive learning improves the discriminative power of graph representations.

Abstract

Advanced graph neural networks have shown great potentials in graph classification tasks recently. Different from node classification where node embeddings aggregated from local neighbors can be directly used to learn node labels, graph classification requires a hierarchical accumulation of different levels of topological information to generate discriminative graph embeddings. Still, how to fully explore graph structures and formulate an effective graph classification pipeline remains rudimentary. In this paper, we propose a novel graph neural network based on supervised contrastive learning with structure inference for graph classification. First, we propose a data-driven graph augmentation strategy that can discover additional connections to enhance the existing edge set. Concretely, we resort to a structure inference stage based on diffusion cascades to recover possible connections with high node similarities. Second, to improve the contrastive power of graph neural networks, we propose to use a supervised contrastive loss for graph classification. With the integration of label information, the one-vs-many contrastive learning can be extended to a many-vs-many setting, so that the graph-level embeddings with higher topological similarities will be pulled closer. The supervised contrastive loss and structure inference can be naturally incorporated within the hierarchical graph neural networks where the topological patterns can be fully explored to produce discriminative graph embeddings. Experiment results show the effectiveness of the proposed method compared with recent state-of-the-art methods.