# Heterogeneous Deep Graph Infomax

arXiv: https://arxiv.org/abs/1911.08538 · HTML: https://mlsanity.com/paper/1911.08538/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2019.

## Built on by (most cited first, 30 of 42)

- [Graph Self-Supervised Learning: A Survey](https://mlsanity.com/paper/2103.00111/) (2021)
- [Graph Contrastive Learning Automated](https://mlsanity.com/paper/2106.07594/) (2021)
- [Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive](https://mlsanity.com/paper/2105.07342/) (2021)
- [Boost then Convolve: Gradient Boosting Meets Graph Neural Networks](https://mlsanity.com/paper/2101.08543/) (2021)
- [Prototypical Graph Contrastive Learning](https://mlsanity.com/paper/2106.09645/) (2021)
- [HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networks](https://mlsanity.com/paper/2310.15318/) (2023)
- [Self-supervised Heterogeneous Graph Pre-training Based on Structural Clustering](https://mlsanity.com/paper/2210.10462/) (2022)
- [Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations](https://mlsanity.com/paper/2201.01702/) (2022)
- [Adversarial Active Learning based Heterogeneous Graph Neural Network for Fake News Detection](https://mlsanity.com/paper/2101.11206/) (2021)
- [Augmentation-Free Graph Contrastive Learning of Invariant-Discriminative Representations](https://mlsanity.com/paper/2210.08345/) (2022)
- [Detecting Communities from Heterogeneous Graphs: A Context Path-based Graph Neural Network Model](https://mlsanity.com/paper/2109.02058/) (2021)
- [Deep Graph Learning for Anomalous Citation Detection](https://mlsanity.com/paper/2202.11360/) (2022)
- [Heterogeneous Graph Contrastive Multi-view Learning](https://mlsanity.com/paper/2210.00248/) (2022)
- [Label Contrastive Coding based Graph Neural Network for Graph Classification](https://mlsanity.com/paper/2101.05486/) (2021)
- [Data Augmentation on Graphs: A Technical Survey](https://mlsanity.com/paper/2212.09970/) (2022)
- [Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative Samples](https://mlsanity.com/paper/2212.13847/) (2022)
- [MECCH: Metapath Context Convolution-based Heterogeneous Graph Neural Networks](https://mlsanity.com/paper/2211.12792/) (2022)
- [Heterogeneous Graph Learning for Explainable Recommendation over Academic Networks](https://mlsanity.com/paper/2202.07832/) (2022)
- [Representation learning in multiplex graphs: Where and how to fuse information?](https://mlsanity.com/paper/2402.17906/) (2024)
- [Graph Prompting for Graph Learning Models: Recent Advances and Future Directions](https://mlsanity.com/paper/2506.08326/) (2025)
- [GSim: A Graph Neural Network based Relevance Measure for Heterogeneous Graphs](https://mlsanity.com/paper/2208.06144/) (2022)
- [Unifying Graph Contrastive Learning via Graph Message Augmentation](https://mlsanity.com/paper/2401.03638/) (2024)
- [HHGT: Hierarchical Heterogeneous Graph Transformer for Heterogeneous Graph Representation Learning](https://mlsanity.com/paper/2407.13158/) (2024)
- [Molecular Graph Representation Learning Integrating Large Language Models with Domain-specific Small Models](https://mlsanity.com/paper/2408.10124/) (2024)
- [A Framework for Joint Unsupervised Learning of Cluster-Aware Embedding for Heterogeneous Networks](https://mlsanity.com/paper/2108.03953/) (2021)
- [Adaptive Multi-layer Contrastive Graph Neural Networks](https://mlsanity.com/paper/2109.14159/) (2021)
- [CGCL: Collaborative Graph Contrastive Learning without Handcrafted Graph Data Augmentations](https://mlsanity.com/paper/2111.03262/) (2021)
- [Representation Learning on Heterostructures via Heterogeneous Anonymous Walks](https://mlsanity.com/paper/2201.06972/) (2022)
- [Geometry Contrastive Learning on Heterogeneous Graphs](https://mlsanity.com/paper/2206.12547/) (2022)
- [Multi-View MOOC Quality Evaluation via Information-Aware Graph Representation Learning](https://mlsanity.com/paper/2301.01593/) (2023)

## Abstract (arXiv)

Graph representation learning is to learn universal node representations that preserve both node attributes and structural information. The derived node representations can be used to serve various downstream tasks, such as node classification and node clustering. When a graph is heterogeneous, the problem becomes more challenging than the homogeneous graph node learning problem. Inspired by the emerging information theoretic-based learning algorithm, in this paper we propose an unsupervised graph neural network Heterogeneous Deep Graph Infomax (HDGI) for heterogeneous graph representation learning. We use the meta-path structure to analyze the connections involving semantics in heterogeneous graphs and utilize graph convolution module and semantic-level attention mechanism to capture local representations. By maximizing local-global mutual information, HDGI effectively learns high-level node representations that can be utilized in downstream graph-related tasks. Experiment results show that HDGI remarkably outperforms state-of-the-art unsupervised graph representation learning methods on both classification and clustering tasks. By feeding the learned representations into a parametric model, such as logistic regression, we even achieve comparable performance in node classification tasks when comparing with state-of-the-art supervised end-to-end GNN models.