# Heterogeneous Graph Contrastive Multi-view Learning

arXiv: https://arxiv.org/abs/2210.00248 · HTML: https://mlsanity.com/paper/2210.00248/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 41 references that are in the map.
- First posted on arXiv 1 Oct 2022.

## Builds on (most cited first, 30 of 32)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Deep Graph Contrastive Representation Learning](https://mlsanity.com/paper/2006.04131/) (2020)
- [Graph Contrastive Learning with Adaptive Augmentation](https://mlsanity.com/paper/2010.14945/) (2020)
- [Diffusion Improves Graph Learning](https://mlsanity.com/paper/1911.05485/) (2019)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Debiased Contrastive Learning](https://mlsanity.com/paper/2007.00224/) (2020)
- [MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding](https://mlsanity.com/paper/2002.01680/) (2020)
- [Large-Scale Representation Learning on Graphs via Bootstrapping](https://mlsanity.com/paper/2102.06514/) (2021)
- [Heterogeneous Information Network Embedding for Recommendation](https://mlsanity.com/paper/1711.10730/) (2017)
- [Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning](https://mlsanity.com/paper/2105.09111/) (2021)
- [An Empirical Study of Graph Contrastive Learning](https://mlsanity.com/paper/2109.01116/) (2021)
- [PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks](https://mlsanity.com/paper/1508.00200/) (2015)
- [Unsupervised Attributed Multiplex Network Embedding](https://mlsanity.com/paper/1911.06750/) (2019)
- [HDMI: High-order Deep Multiplex Infomax](https://mlsanity.com/paper/2102.07810/) (2021)

## Built on by (most cited first, 14 of 14)

- [GFT: Graph Foundation Model with Transferable Tree Vocabulary](https://mlsanity.com/paper/2411.06070/) (2024)
- [Edge Prompt Tuning for Graph Neural Networks](https://mlsanity.com/paper/2503.00750/) (2025)
- [Beyond Message Passing: Neural Graph Pattern Machine](https://mlsanity.com/paper/2501.18739/) (2025)
- [When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning](https://mlsanity.com/paper/2409.00687/) (2024)
- [Generative Graph Pattern Machine](https://mlsanity.com/paper/2505.16130/) (2025)
- [Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective](https://mlsanity.com/paper/2412.00742/) (2024)
- [Semantic Refinement with LLMs for Graph Representations](https://mlsanity.com/paper/2512.21106/) (2025)
- [Temporal Graph Pattern Machine](https://mlsanity.com/paper/2601.22454/) (2026)
- [TPGNN: Learning High-order Information in Dynamic Graphs via Temporal Propagation](https://mlsanity.com/paper/2210.01171/) (2022)
- [HG-Adapter: Improving Pre-Trained Heterogeneous Graph Neural Networks with Dual Adapters](https://mlsanity.com/paper/2411.01155/) (2024)
- [CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts](https://mlsanity.com/paper/2605.15888/) (2026)
- [M2HGCL: Multi-Scale Meta-Path Integrated Heterogeneous Graph Contrastive Learning](https://mlsanity.com/paper/2309.01101/) (2023)
- [Generative-Contrastive Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2404.02810/) (2024)
- [Incorporating Attributes and Multi-Scale Structures for Heterogeneous Graph Contrastive Learning](https://mlsanity.com/paper/2503.13911/) (2025)

## Abstract (arXiv)

Inspired by the success of contrastive learning (CL) in computer vision and natural language processing, graph contrastive learning (GCL) has been developed to learn discriminative node representations on graph datasets. However, the development of GCL on Heterogeneous Information Networks (HINs) is still in the infant stage. For example, it is unclear how to augment the HINs without substantially altering the underlying semantics, and how to design the contrastive objective to fully capture the rich semantics. Moreover, early investigations demonstrate that CL suffers from sampling bias, whereas conventional debiasing techniques are empirically shown to be inadequate for GCL. How to mitigate the sampling bias for heterogeneous GCL is another important problem. To address the aforementioned challenges, we propose a novel Heterogeneous Graph Contrastive Multi-view Learning (HGCML) model. In particular, we use metapaths as the augmentation to generate multiple subgraphs as multi-views, and propose a contrastive objective to maximize the mutual information between any pairs of metapath-induced views. To alleviate the sampling bias, we further propose a positive sampling strategy to explicitly select positives for each node via jointly considering semantic and structural information preserved on each metapath view. Extensive experiments demonstrate HGCML consistently outperforms state-of-the-art baselines on five real-world benchmark datasets.