# HeteGraph-Mamba: Heterogeneous Graph Learning via Selective State Space Model

arXiv: https://arxiv.org/abs/2405.13915 · HTML: https://mlsanity.com/paper/2405.13915/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 20 of its 27 references that are in the map.
- First posted on arXiv 22 May 2024.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)

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

- [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)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs](https://mlsanity.com/paper/2103.09430/) (2021)
- [MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding](https://mlsanity.com/paper/2002.01680/) (2020)
- [Pure Transformers are Powerful Graph Learners](https://mlsanity.com/paper/2207.02505/) (2022)
- [Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks](https://mlsanity.com/paper/2112.14936/) (2021)
- [Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2402.00789/) (2024)
- [A Generalization of ViT/MLP-Mixer to Graphs](https://mlsanity.com/paper/2212.13350/) (2022)
- [An Attention-based Graph Neural Network for Heterogeneous Structural Learning](https://mlsanity.com/paper/1912.10832/) (2019)
- [Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation](https://mlsanity.com/paper/2403.18257/) (2024)
- [HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformer](https://mlsanity.com/paper/2302.11329/) (2023)
- [DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks](https://mlsanity.com/paper/2010.03250/) (2020)
- [Scalable Graph Neural Networks for Heterogeneous Graphs](https://mlsanity.com/paper/2011.09679/) (2020)
- [Long-range Meta-path Search on Large-scale Heterogeneous Graphs](https://mlsanity.com/paper/2307.08430/) (2023)

## Built on by (most cited first, 3 of 3)

- [What Can We Learn from State Space Models for Machine Learning on Graphs?](https://mlsanity.com/paper/2406.05815/) (2024)
- [Exploring Graph Mamba: A Comprehensive Survey on State-Space Models for Graph Learning](https://mlsanity.com/paper/2412.18322/) (2024)
- [Graph Mamba Survival Analysis Based on Topology-Aware ordering](https://mlsanity.com/paper/2606.02602/) (2026)

## Abstract (arXiv)

We propose a heterogeneous graph mamba network (HGMN) as the first exploration in leveraging the selective state space models (SSSMs) for heterogeneous graph learning. Compared with the literature, our HGMN overcomes two major challenges: (i) capturing long-range dependencies among heterogeneous nodes and (ii) adapting SSSMs to heterogeneous graph data. Our key contribution is a general graph architecture that can solve heterogeneous nodes in real-world scenarios, followed an efficient flow. Methodologically, we introduce a two-level efficient tokenization approach that first captures long-range dependencies within identical node types, and subsequently across all node types. Empirically, we conduct comparisons between our framework and 19 state-of-the-art methods on the heterogeneous benchmarks. The extensive comparisons demonstrate that our framework outperforms other methods in both the accuracy and efficiency dimensions.