# Motif-Driven Contrastive Learning of Graph Representations

arXiv: https://arxiv.org/abs/2012.12533 · HTML: https://mlsanity.com/paper/2012.12533/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2020.

## Built on by (most cited first, 4 of 4)

- [Let Invariant Rationale Discovery Inspire Graph Contrastive Learning](https://mlsanity.com/paper/2206.07869/) (2022)
- [Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphs](https://mlsanity.com/paper/2110.01191/) (2021)
- [Molecular Representation Learning via Heterogeneous Motif Graph Neural Networks](https://mlsanity.com/paper/2202.00529/) (2022)
- [Graph Prompting for Graph Learning Models: Recent Advances and Future Directions](https://mlsanity.com/paper/2506.08326/) (2025)

## Abstract (arXiv)

Pre-training Graph Neural Networks (GNN) via self-supervised contrastive learning has recently drawn lots of attention. However, most existing works focus on node-level contrastive learning, which cannot capture global graph structure. The key challenge to conducting subgraph-level contrastive learning is to sample informative subgraphs that are semantically meaningful. To solve it, we propose to learn graph motifs, which are frequently-occurring subgraph patterns (e.g. functional groups of molecules), for better subgraph sampling. Our framework MotIf-driven Contrastive leaRning Of Graph representations (MICRO-Graph) can: 1) use GNNs to extract motifs from large graph datasets; 2) leverage learned motifs to sample informative subgraphs for contrastive learning of GNN. We formulate motif learning as a differentiable clustering problem, and adopt EM-clustering to group similar and significant subgraphs into several motifs. Guided by these learned motifs, a sampler is trained to generate more informative subgraphs, and these subgraphs are used to train GNNs through graph-to-subgraph contrastive learning. By pre-training on the ogbg-molhiv dataset with MICRO-Graph, the pre-trained GNN achieves 2.04% ROC-AUC average performance enhancement on various downstream benchmark datasets, which is significantly higher than other state-of-the-art self-supervised learning baselines.