mlsanityData to 7 Oct 2026

Memory-Based Graph Networks

arXiv 2002.09518 ↗First posted 21 Feb 2020cs.LG cs.NE stat.MLcited by 56

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) are a class of deep models that operate on data with arbitrary topology represented as graphs. We introduce an efficient memory layer for GNNs that can jointly learn node representations and coarsen the graph. We also introduce two new networks based on this layer: memory-based GNN (MemGNN) and graph memory network (GMN) that can learn hierarchical graph representations. The experimental results shows that the proposed models achieve state-of-the-art results in eight out of nine graph classification and regression benchmarks. We also show that the learned representations could correspond to chemical features in the molecule data. Code and reference implementations are released at: https://github.com/amirkhas/GraphMemoryNet

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 17; 2023: 9; 2024: 9; 2025: 5; 2026: 2.

56 papers.

Sort:

  1. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 326
  2. 2022Representing Long-Range Context for Graph Neural Networks with Global Attentioncited by 193
  3. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  4. 2021Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Futurecited by 67
  5. 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunitiescited by 52
  6. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  7. 2021Pooling Architecture Search for Graph Classificationcited by 36
  8. 2021Graph Domain Adaptation: A Generative Viewcited by 35
  9. 2023The expressive power of pooling in Graph Neural Networkscited by 35
  10. 2021Distribution Knowledge Embedding for Graph Poolingcited by 19
  11. 2022Cross-Domain Few-Shot Graph Classificationcited by 19
  12. 2024Learning Graph Quantized Tokenizerscited by 19
38 more
  1. 2022KGNN: Harnessing Kernel-based Networks for Semi-supervised Graph Classificationcited by 18
  2. 2022Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networkscited by 18
  3. 2021Graph Pooling via Coarsened Graph Infomaxcited by 15
  4. 2022Learning Graph Augmentations to Learn Graph Representationscited by 14
  5. 2023Classification of Edge-dependent Labels of Nodes in Hypergraphscited by 14
  6. 2022TopoImb: Toward Topology-level Imbalance in Learning from Graphscited by 12
  7. 2024Subgraph-level Universal Prompt Tuningcited by 9
  8. 2022PatchGT: Transformer over Non-trainable Clusters for Learning Graph Representationscited by 8
  9. 2021Diversified Multiscale Graph Learning with Graph Self-Correctioncited by 6
  10. 2022Generalizing Downsampling from Regular Data to Graphscited by 6
  11. 2025ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL Problemscited by 6
  12. 2022Grouping-matrix based Graph Pooling with Adaptive Number of Clusterscited by 5
  13. 2023Curvature-based Pooling within Graph Neural Networkscited by 5
  14. 2024MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networkscited by 5
  15. 2021Blockchain Phishing Scam Detection via Multi-channel Graph Classificationcited by 4
  16. 2023Personalized Federated Domain Adaptation for Item-to-Item Recommendationcited by 4
  17. 2023On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Poolingcited by 4
  18. 2024Disambiguated Node Classification with Graph Neural Networkscited by 4
  19. 2024Graph Parsing Networkscited by 4
  20. 2024Multi-source Unsupervised Domain Adaptation on Graphs with Transferability Modelingcited by 4
  21. 2022Material Prediction for Design Automation Using Graph Representation Learningcited by 3
  22. 2024Beyond Grid Data: Exploring Graph Neural Networks for Earth Observationcited by 3
  23. 2025UniGO: A Unified Graph Neural Network for Modeling Opinion Dynamics on Graphscited by 3
  24. 2025GENUINE: Graph Enhanced Multi-level Uncertainty Estimation for Large Language Modelscited by 3
  25. 2021MassFormer: Tandem Mass Spectrum Prediction for Small Molecules using Graph Transformerscited by 2
  26. 2022Automatic Identification of Chemical Moietiescited by 2
  27. 2022Tackling Provably Hard Representative Selection via Graph Neural Networkscited by 2
  28. 2022Memory-Augmented Graph Neural Networks: A Brain-Inspired Reviewcited by 2
  29. 2023Exploiting Graph Structured Cross-Domain Representation for Multi-Domain Recommendationcited by 2
  30. 2025BN-Pool: Bayesian Nonparametric Pooling for Graphscited by 2
  31. 2021ChebLieNet: Invariant Spectral Graph NNs Turned Equivariant by Riemannian Geometry on Lie Groupscited by 1
  32. 2023Careful Selection and Thoughtful Discarding: Graph Explicit Pooling Utilizing Discarded Nodescited by 1
  33. 2023Enhance Sketch Recognition's Explainability via Semantic Component-Level Parsingcited by 1
  34. 2024Edge-Based Graph Component Poolingcited by 1
  35. 2021CNN with large memory layerscited by 0
  36. 2021Memory Capacity of Recurrent Neural Networks with Matrix Representationcited by 0
  37. 2022Boosting Graph Neural Networks by Injecting Pooling in Message Passingcited by 0
  38. 2022Graph-level Neural Networks: Current Progress and Future Directionscited by 0

50 most cited of 56 All 56 (JSON)