# M2HGCL: Multi-Scale Meta-Path Integrated Heterogeneous Graph Contrastive Learning

arXiv: https://arxiv.org/abs/2309.01101 · HTML: https://mlsanity.com/paper/2309.01101/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 26 references that are in the map.
- First posted on arXiv 3 Sep 2023.

## Builds on (most cited first, 20 of 20)

- [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)
- [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)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (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)
- [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)
- [Heterogeneous Deep Graph Infomax](https://mlsanity.com/paper/1911.08538/) (2019)
- [Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs](https://mlsanity.com/paper/2007.08294/) (2020)
- [Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks](https://mlsanity.com/paper/2012.10024/) (2020)
- [Heterogeneous Graph Contrastive Multi-view Learning](https://mlsanity.com/paper/2210.00248/) (2022)

## Abstract (arXiv)

Inspired by the successful application of contrastive learning on graphs, researchers attempt to impose graph contrastive learning approaches on heterogeneous information networks. Orthogonal to homogeneous graphs, the types of nodes and edges in heterogeneous graphs are diverse so that specialized graph contrastive learning methods are required. Most existing methods for heterogeneous graph contrastive learning are implemented by transforming heterogeneous graphs into homogeneous graphs, which may lead to ramifications that the valuable information carried by non-target nodes is undermined thereby exacerbating the performance of contrastive learning models. Additionally, current heterogeneous graph contrastive learning methods are mainly based on initial meta-paths given by the dataset, yet according to our deep-going exploration, we derive empirical conclusions: only initial meta-paths cannot contain sufficiently discriminative information; and various types of meta-paths can effectively promote the performance of heterogeneous graph contrastive learning methods. To this end, we propose a new multi-scale meta-path integrated heterogeneous graph contrastive learning (M2HGCL) model, which discards the conventional heterogeneity-homogeneity transformation and performs the graph contrastive learning in a joint manner. Specifically, we expand the meta-paths and jointly aggregate the direct neighbor information, the initial meta-path neighbor information and the expanded meta-path neighbor information to sufficiently capture discriminative information. A specific positive sampling strategy is further imposed to remedy the intrinsic deficiency of contrastive learning, i.e., the hard negative sample sampling issue. Through extensive experiments on three real-world datasets, we demonstrate that M2HGCL outperforms the current state-of-the-art baseline models.