mlsanityData to 14 Oct 2026

Long Range Graph Benchmark

arXiv 2206.08164 ↗First posted 16 Jun 2022cs.LGcited by 263

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) that are based on the message passing (MP) paradigm generally exchange information between 1-hop neighbors to build node representations at each layer. In principle, such networks are not able to capture long-range interactions (LRI) that may be desired or necessary for learning a given task on graphs. Recently, there has been an increasing interest in development of Transformer-based methods for graphs that can consider full node connectivity beyond the original sparse structure, thus enabling the modeling of LRI. However, MP-GNNs that simply rely on 1-hop message passing often fare better in several existing graph benchmarks when combined with positional feature representations, among other innovations, hence limiting the perceived utility and ranking of Transformer-like architectures. Here, we present the Long Range Graph Benchmark (LRGB) with 5 graph learning datasets: PascalVOC-SP, COCO-SP, PCQM-Contact, Peptides-func and Peptides-struct that arguably require LRI reasoning to achieve strong performance in a given task. We benchmark both baseline GNNs and Graph Transformer networks to verify that the models which capture long-range dependencies perform significantly better on these tasks. Therefore, these datasets are suitable for benchmarking and exploration of MP-GNNs and Graph Transformer architectures that are intended to capture LRI.

Key facts. Cited by 263 papers in the map (data through 14 Oct 2026). Builds on 46 of its 76 references that are in the map. First posted on arXiv 16 Jun 2022.

Builds on

46 of 76 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2017Graph Attention Networkscited by 8,923
  6. 2018How Powerful are Graph Neural Networks?cited by 4,393
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  9. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  10. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  11. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  12. 2019Strategies for Pre-training Graph Neural Networkscited by 971
34 more
  1. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
  2. 2020Simple and Deep Graph Convolutional Networkscited by 860
  3. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  4. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 713
  5. 2020Long Range Arena: A Benchmark for Efficient Transformerscited by 700
  6. 2020Benchmarking Graph Neural Networkscited by 680
  7. 2020A Generalization of Transformer Networks to Graphscited by 661
  8. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  9. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 631
  10. 2021Rethinking Graph Transformers with Spectral Attentioncited by 473
  11. 2017Residual Gated Graph ConvNetscited by 346
  12. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 333
  13. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 329
  14. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 313
  15. 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248
  16. 2021Weisfeiler and Lehman Go Cellular: CW Networkscited by 218
  17. 2020Design Space for Graph Neural Networkscited by 182
  18. 2022Sign and Basis Invariant Networks for Spectral Graph Representation Learningcited by 179
  19. 2021Learning Gradient Fields for Molecular Conformation Generationcited by 163
  20. 2021GraphiT: Encoding Graph Structure in Transformerscited by 147
  21. 20213D Infomax improves GNNs for Molecular Property Predictioncited by 146
  22. 2021Nested Graph Neural Networkscited by 137
  23. 2021GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensemblescited by 107
  24. 2020Implicit Graph Neural Networkscited by 100
  25. 2021Learning Neural Generative Dynamics for Molecular Conformation Generationcited by 88
  26. 2021New Benchmarks for Learning on Non-Homophilous Graphscited by 81
  27. 2022Benchmarking Graphormer on Large-Scale Molecular Modeling Datasetscited by 64
  28. 2021Graph Neural Networks Inspired by Classical Iterative Algorithmscited by 60
  29. 2020A Large-Scale Database for Graph Representation Learningcited by 55
  30. 2021Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphscited by 35
  31. 2022EIGNN: Efficient Infinite-Depth Graph Neural Networkscited by 32
  32. 2020Graph Networks with Spectral Message Passingcited by 17
  33. 2022A Unified Framework for Rank-based Evaluation Metrics for Link Prediction in Knowledge Graphscited by 15
  34. 2021Hierarchical graph neural nets can capture long-range interactionscited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 56; 2024: 82; 2025: 70; 2026: 49.

263 papers.

Sort:

By area:

  1. 2023Exploring the Potential of Large Language Models (LLMs) in Learning on Graphscited by 274
  2. 2023Exphormer: Sparse Transformers for Graphscited by 170
  3. 2023Graph Inductive Biases in Transformers without Message Passingcited by 153
  4. 2024Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spacescited by 134
  5. 2023Graph Foundation Models: Concepts, Opportunities and Challengescited by 103
  6. 2022Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvaturecited by 98
  7. 2023Understanding Oversquashing in GNNs through the Lens of Effective Resistancecited by 97
  8. 2022A Generalization of ViT/MLP-Mixer to Graphscited by 93
  9. 2024Graph Mamba: Towards Learning on Graphs with State Space Modelscited by 86
  10. 2023Where Did the Gap Go? Reassessing the Long-Range Graph Benchmarkcited by 85
  11. 2023A Survey of Graph Meets Large Language Model: Progress and Future Directionscited by 85
  12. 2023DRew: Dynamically Rewired Message Passing with Delaycited by 82
38 more
  1. 2022On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networkscited by 64
  2. 2023On the Connection Between MPNN and Graph Transformercited by 61
  3. 2023Locality-Aware Graph-Rewiring in GNNscited by 56
  4. 2022Oversquashing in GNNs through the lens of information contraction and graph expansioncited by 53
  5. 2025Position: Graph Learning Will Lose Relevance Due To Poor Benchmarkscited by 53
  6. 2023GSLB: The Graph Structure Learning Benchmarkcited by 50
  7. 2024KAGNNs: Kolmogorov-Arnold Networks meet Graph Learningcited by 49
  8. 2025On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learningcited by 43
  9. 2023Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvaturecited by 41
  10. 2023Cooperative Graph Neural Networkscited by 36
  11. 2024TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphscited by 36
  12. 2023Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priorscited by 34
  13. 2024VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connectionscited by 34
  14. 2023Graph Positional and Structural Encodercited by 33
  15. 2023Path Neural Networks: Expressive and Accurate Graph Neural Networkscited by 32
  16. 2024Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learningcited by 29
  17. 2024Long Range Propagation on Continuous-Time Dynamic Graphscited by 28
  18. 2023Learning Probabilistic Symmetrization for Architecture Agnostic Equivariancecited by 26
  19. 2023Probabilistically Rewired Message-Passing Neural Networkscited by 26
  20. 2023From Continuous Dynamics to Graph Neural Networks: Neural Diffusion and Beyondcited by 26
  21. 2025Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellencecited by 26
  22. 2023Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreachingcited by 24
  23. 2025Learning Efficient Positional Encodings with Graph Neural Networkscited by 24
  24. 2022Transformers over Directed Acyclic Graphscited by 23
  25. 2023Graph-level Representation Learning with Joint-Embedding Predictive Architecturescited by 22
  26. 2023Exposition on over-squashing problem on GNNs: Current Methods, Benchmarks and Challengescited by 22
  27. 2024Cayley Graph Propagationcited by 21
  28. 2023Fragment-based Pretraining and Finetuning on Molecular Graphscited by 20
  29. 2024Distinguished In Uniform: Self Attention Vs. Virtual Nodescited by 20
  30. 2025Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurementcited by 20
  31. 2024Learning Graph Quantized Tokenizerscited by 19
  32. 2025Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learningcited by 19
  33. 2024Learning Long Range Dependencies on Graphs via Random Walkscited by 18
  34. 2024Spatio-Spectral Graph Neural Networkscited by 17
  35. 2025Beyond Message Passing: Neural Graph Pattern Machinecited by 17
  36. 2023Improving Graph Generation by Restricting Graph Bandwidthcited by 16
  37. 2023Enhancing Graph Transformers with Hierarchical Distance Structural Encodingcited by 16
  38. 2025No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasetscited by 16

50 most cited of 263 All 263 (JSON)