# Pairwise Half-graph Discrimination: A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks

arXiv: https://arxiv.org/abs/2110.13567 · HTML: https://mlsanity.com/paper/2110.13567/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 26 Oct 2021.

## Builds on (most cited first, 17 of 17)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Self-supervised Learning: Generative or Contrastive](https://mlsanity.com/paper/2006.08218/) (2020)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [Representation Learning on Graphs: Methods and Applications](https://mlsanity.com/paper/1709.05584/) (2017)
- [InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization](https://mlsanity.com/paper/1908.01000/) (2019)
- [GPT-GNN: Generative Pre-Training of Graph Neural Networks](https://mlsanity.com/paper/2006.15437/) (2020)
- [Towards Deeper Graph Neural Networks](https://mlsanity.com/paper/2007.09296/) (2020)
- [DeeperGCN: All You Need to Train Deeper GCNs](https://mlsanity.com/paper/2006.07739/) (2020)
- [graph2vec: Learning Distributed Representations of Graphs](https://mlsanity.com/paper/1707.05005/) (2017)
- [Artificial Intelligence and Statistics](https://mlsanity.com/paper/1712.03779/) (2017)

## Built on by (most cited first, 10 of 10)

- [A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications](https://mlsanity.com/paper/2202.07893/) (2022)
- [When to Pre-Train Graph Neural Networks? From Data Generation Perspective!](https://mlsanity.com/paper/2303.16458/) (2023)
- [Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks](https://mlsanity.com/paper/2311.01038/) (2023)
- [A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective](https://mlsanity.com/paper/2403.16137/) (2024)
- [Towards A Universal Graph Structural Encoder](https://mlsanity.com/paper/2504.10917/) (2025)
- [Neural Graph Matching for Pre-training Graph Neural Networks](https://mlsanity.com/paper/2203.01597/) (2022)
- [Self-supervised Learning and Graph Classification under Heterophily](https://mlsanity.com/paper/2306.08469/) (2023)
- [CandidateDrug4Cancer: An Open Molecular Graph Learning Benchmark on Drug Discovery for Cancer](https://mlsanity.com/paper/2203.00836/) (2022)
- [HCL: Improving Graph Representation with Hierarchical Contrastive Learning](https://mlsanity.com/paper/2210.12020/) (2022)
- [Topology Matters: A Cautionary Case Study of Graph SSL on Neuro-Inspired Benchmarks](https://mlsanity.com/paper/2602.03217/) (2026)

## Abstract (arXiv)

Self-supervised learning has gradually emerged as a powerful technique for graph representation learning. However, transferable, generalizable, and robust representation learning on graph data still remains a challenge for pre-training graph neural networks. In this paper, we propose a simple and effective self-supervised pre-training strategy, named Pairwise Half-graph Discrimination (PHD), that explicitly pre-trains a graph neural network at graph-level. PHD is designed as a simple binary classification task to discriminate whether two half-graphs come from the same source. Experiments demonstrate that the PHD is an effective pre-training strategy that offers comparable or superior performance on 13 graph classification tasks compared with state-of-the-art strategies, and achieves notable improvements when combined with node-level strategies. Moreover, the visualization of learned representation revealed that PHD strategy indeed empowers the model to learn graph-level knowledge like the molecular scaffold. These results have established PHD as a powerful and effective self-supervised learning strategy in graph-level representation learning.