HeteGraph-Mamba: Heterogeneous Graph Learning via Selective State Space Model
On the map: State-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
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.
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.
Builds on
20 of 27 references.
Closest ancestors · 1
Same direction, newest first
Other references · 19
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
- 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
- 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
- 2019Graph Transformer Networkscited by 523
- 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 329
- 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
- 2022Pure Transformers are Powerful Graph Learnerscited by 188
- 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
7 more
- 2022A Generalization of ViT/MLP-Mixer to Graphscited by 93
- 2019An Attention-based Graph Neural Network for Heterogeneous Structural Learningcited by 71
- 2024Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separationcited by 45
- 2023HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformercited by 35
- 2020DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networkscited by 34
- 2020Scalable Graph Neural Networks for Heterogeneous Graphscited by 31
- 2023Long-range Meta-path Search on Large-scale Heterogeneous Graphscited by 4
Built on by
Citing papers per year: 2024: 2; 2025: 0; 2026: 1.
3 papers.
Similar, not cited
Close in wording, no citation either way
- 2024Graph Mamba: Towards Learning on Graphs with State Space Models
- 2024DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models
- 2025Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space
- 2025Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling
- 2025Dual Mamba for Node-Specific Representation Learning: Tackling Over-Smoothing with Selective State Space Modeling
- 2024Teaching MLPs to Master Heterogeneous Graph-Structured Knowledge for Efficient and Accurate Inference
- 2024STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model
- 2025MAPN: Enhancing Heterogeneous Sparse Graph Representation by Mamba-based Asynchronous Aggregation