mlsanityData to 14 Oct 2026

MAPN: Enhancing Heterogeneous Sparse Graph Representation by Mamba-based Asynchronous Aggregation

arXiv 2502.16454 ↗First posted 23 Feb 2025cs.LGcited by 1

On the map: State-space sequence models (S4, Mamba) → Video, motion and generative Mamba models

Abstract (arXiv)

Graph neural networks (GNNs) have become the state of the art for various graph-related tasks and are particularly prominent in heterogeneous graphs (HetGs). However, several issues plague this paradigm: first, the difficulty in fully utilizing long-range information, known as over-squashing; second, the tendency for excessive message-passing layers to produce indistinguishable representations, referred to as over-smoothing; and finally, the inadequacy of conventional MPNNs to train effectively on large sparse graphs. To address these challenges in deep neural networks for large-scale heterogeneous graphs, this paper introduces the Mamba-based Asynchronous Propagation Network (MAPN), which enhances the representation of heterogeneous sparse graphs. MAPN consists of two primary components: node sequence generation and semantic information aggregation. Node sequences are initially generated based on meta-paths through random walks, which serve as the foundation for a spatial state model that extracts essential information from nodes at various distances. It then asynchronously aggregates semantic information across multiple hops and layers, effectively preserving unique node characteristics and mitigating issues related to deep network degradation. Extensive experiments across diverse datasets demonstrate the effectiveness of MAPN in graph embeddings for various downstream tasks underscoring its substantial benefits for graph representation in large sparse heterogeneous graphs.

Key facts. Cited by 1 paper 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 33 of its 48 references that are in the map. First posted on arXiv 23 Feb 2025.

Builds on

33 of 48 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  6. 2018How Powerful are Graph Neural Networks?cited by 4,393
  7. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  8. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  9. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  10. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  11. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  12. 2019Heterogeneous Graph Attention Networkcited by 734
21 more
  1. 2020Heterogeneous Graph Transformercited by 582
  2. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
  3. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 506
  4. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 478
  5. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  6. 2022Long Range Graph Benchmarkcited by 263
  7. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  8. 2023DRew: Dynamically Rewired Message Passing with Delaycited by 82
  9. 2022Simple and Efficient Heterogeneous Graph Neural Networkcited by 71
  10. 2023Towards Understanding the Generalization of Graph Neural Networkscited by 41
  11. 2023HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networkscited by 33
  12. 2021Heterogeneous Graph Representation Learning with Relation Awarenesscited by 31
  13. 2023PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Predictioncited by 25
  14. 2023Generative Flow Network for Listwise Recommendationcited by 19
  15. 2023No prejudice! Fair Federated Graph Neural Networks for Personalized Recommendationcited by 18
  16. 2021Relation-aware Heterogeneous Graph for User Profilingcited by 9
  17. 2023KGTrust: Evaluating Trustworthiness of SIoT via Knowledge Enhanced Graph Neural Networkscited by 9
  18. 2023AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Networkcited by 7
  19. 2023HAGNN: Hybrid Aggregation for Heterogeneous Graph Neural Networkscited by 4
  20. 2024Exit Ripple Effects: Understanding the Disruption of Socialization Networks Following Employee Departurescited by 3
  21. 2025HetFS: A Method for Fast Similarity Search with Ad-hoc Meta-paths on Heterogeneous Information Networkscited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modelingcited by 11

Similar, not cited

Close in wording, no citation either way

  1. 2025Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space
  2. 2024Graph Mamba: Towards Learning on Graphs with State Space Models
  3. 2024Sparse Decomposition of Graph Neural Networks
  4. 2024HeteGraph-Mamba: Heterogeneous Graph Learning via Selective State Space Model
  5. 2025Dual Mamba for Node-Specific Representation Learning: Tackling Over-Smoothing with Selective State Space Modeling
  6. 2023Graph Condensation for Inductive Node Representation Learning
  7. 2025Spiking Heterogeneous Graph Attention Networks
  8. 2024Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach