mlsanityData to 14 Oct 2026

Hierarchical Inter-Message Passing for Learning on Molecular Graphs

arXiv 2006.12179 ↗First posted 22 Jun 2020cs.LG stat.MLcited by 59

Not on the map. Why?

Abstract (arXiv)

We present a hierarchical neural message passing architecture for learning on molecular graphs. Our model takes in two complementary graph representations: the raw molecular graph representation and its associated junction tree, where nodes represent meaningful clusters in the original graph, e.g., rings or bridged compounds. We then proceed to learn a molecule's representation by passing messages inside each graph, and exchange messages between the two representations using a coarse-to-fine and fine-to-coarse information flow. Our method is able to overcome some of the restrictions known from classical GNNs, like detecting cycles, while still being very efficient to train. We validate its performance on the ZINC dataset and datasets stemming from the MoleculeNet benchmark collection.

Key facts. Cited by 59 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 14; 2023: 13; 2024: 14; 2025: 4; 2026: 3.

59 papers.

Sort:

  1. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  2. 2021Weisfeiler and Lehman Go Cellular: CW Networkscited by 218
  3. 2022Sign and Basis Invariant Networks for Spectral Graph Representation Learningcited by 179
  4. 2023Exphormer: Sparse Transformers for Graphscited by 170
  5. 2021From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awarenesscited by 155
  6. 2021Equivariant Subgraph Aggregation Networkscited by 154
  7. 2021Weisfeiler and Leman go Machine Learning: The Story so farcited by 122
  8. 2022Understanding and Extending Subgraph GNNs by Rethinking Their Symmetriescited by 112
  9. 2021Graph-Guided Network for Irregularly Sampled Multivariate Time Seriescited by 111
  10. 2024GFT: Graph Foundation Model with Transferable Tree Vocabularycited by 85
  11. 2022Expander Graph Propagationcited by 75
  12. 2022Ordered Subgraph Aggregation Networkscited by 57
38 more
  1. 2022Boosting the Cycle Counting Power of Graph Neural Networks with I2-GNNscited by 56
  2. 2022Your Transformer May Not be as Powerful as You Expectcited by 55
  3. 2022Multimodal learning with graphscited by 54
  4. 2021Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passingcited by 47
  5. 2022Message passing all the way upcited by 47
  6. 2021Autobahn: Automorphism-based Graph Neural Netscited by 39
  7. 2023Equivariant Polynomials for Graph Neural Networkscited by 38
  8. 2023Path Neural Networks: Expressive and Accurate Graph Neural Networkscited by 32
  9. 2023Graph Positional Encoding via Random Feature Propagationcited by 31
  10. 2021Directional Message Passing on Molecular Graphs via Synthetic Coordinatescited by 24
  11. 2022Equivariant Graph Hierarchy-Based Neural Networkscited by 24
  12. 2022Molecular Representation Learning via Heterogeneous Motif Graph Neural Networkscited by 23
  13. 2022Affinity-Aware Graph Networkscited by 17
  14. 2024Spatio-Spectral Graph Neural Networkscited by 17
  15. 2023Learning Topology-Specific Experts for Molecular Property Predictioncited by 15
  16. 2024Probabilistic Graph Rewiring via Virtual Nodescited by 15
  17. 2023CIN++: Enhancing Topological Message Passingcited by 14
  18. 2022Agent-based Graph Neural Networkscited by 13
  19. 2023Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Powercited by 12
  20. 2022Multi stain graph fusion for multimodal integration in pathologycited by 11
  21. 2023PlanE: Representation Learning over Planar Graphscited by 11
  22. 2023Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexescited by 11
  23. 2024A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspectivecited by 9
  24. 2024Expressivity and Generalization: Fragment-Biases for Molecular GNNscited by 9
  25. 2024Learning on Large Graphs using Intersecting Communitiescited by 8
  26. 2024Cluster-wise Graph Transformer with Dual-granularity Kernelized Attentioncited by 8
  27. 2023Self-Attention in Colors: Another Take on Encoding Graph Structure in Transformerscited by 7
  28. 2024Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Surveycited by 6
  29. 2023Curvature-based Pooling within Graph Neural Networkscited by 5
  30. 2023Transformers are efficient hierarchical chemical graph learnerscited by 4
  31. 2024Demystifying Higher-Order Graph Neural Networkscited by 4
  32. 2024Graph External Attention Enhanced Transformercited by 3
  33. 2023P-Tensors: a General Formalism for Constructing Higher Order Message Passing Networkscited by 2
  34. 2024Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learningcited by 2
  35. 2025Efficient Learning on Large Graphs using a Densifying Regularity Lemmacited by 2
  36. 2021Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretrainingcited by 1
  37. 2021An In-depth Summary of Recent Artificial Intelligence Applications in Drug Designcited by 1
  38. 2025Hierarchical geometric deep learning enables scalable analysis of molecular dynamicscited by 1

50 most cited of 59 All 59 (JSON)