mlsanityData to 7 Oct 2026

Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark

arXiv 2309.00367 ↗First posted 1 Sep 2023cs.LGcited by 83

Not on the map. Why?

Abstract (arXiv)

The recent Long-Range Graph Benchmark (LRGB, Dwivedi et al. 2022) introduced a set of graph learning tasks strongly dependent on long-range interaction between vertices. Empirical evidence suggests that on these tasks Graph Transformers significantly outperform Message Passing GNNs (MPGNNs). In this paper, we carefully reevaluate multiple MPGNN baselines as well as the Graph Transformer GPS (Ramp'avsek et al. 2022) on LRGB. Through a rigorous empirical analysis, we demonstrate that the reported performance gap is overestimated due to suboptimal hyperparameter choices. It is noteworthy that across multiple datasets the performance gap completely vanishes after basic hyperparameter optimization. In addition, we discuss the impact of lacking feature normalization for LRGB's vision datasets and highlight a spurious implementation of LRGB's link prediction metric. The principal aim of our paper is to establish a higher standard of empirical rigor within the graph machine learning community.

Key facts. Cited by 83 papers in the map (data through 7 Oct 2026). Builds on 31 of its 37 references that are in the map. First posted on arXiv 1 Sep 2023.

Builds on

31 of 37 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  8. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  9. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  10. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  11. 2020Simple and Deep Graph Convolutional Networkscited by 857
  12. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 702
19 more
  1. 2020Benchmarking Graph Neural Networkscited by 672
  2. 2020A Generalization of Transformer Networks to Graphscited by 653
  3. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
  4. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  5. 2021Rethinking Graph Transformers with Spectral Attentioncited by 468
  6. 2017Residual Gated Graph ConvNetscited by 341
  7. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 326
  8. 2022Long Range Graph Benchmarkcited by 258
  9. 2020DeeperGCN: All You Need to Train Deeper GCNscited by 249
  10. 2022Pure Transformers are Powerful Graph Learnerscited by 188
  11. 2020Design Space for Graph Neural Networkscited by 182
  12. 2023Exphormer: Sparse Transformers for Graphscited by 166
  13. 2023Graph Inductive Biases in Transformers without Message Passingcited by 150
  14. 2022Transformer for Graphs: An Overview from Architecture Perspectivecited by 107
  15. 2022A Generalization of ViT/MLP-Mixer to Graphscited by 93
  16. 2023DRew: Dynamically Rewired Message Passing with Delaycited by 81
  17. 2022GRPE: Relative Positional Encoding for Graph Transformercited by 67
  18. 2023On the Connection Between MPNN and Graph Transformercited by 60
  19. 2021Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passingcited by 46

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 33; 2025: 24; 2026: 18.

83 papers.

Sort:

By area:

  1. 2024Graph Mamba: Towards Learning on Graphs with State Space Modelscited by 84
  2. 2023Locality-Aware Graph-Rewiring in GNNscited by 55
  3. 2025Position: Graph Learning Will Lose Relevance Due To Poor Benchmarkscited by 52
  4. 2023Cooperative Graph Neural Networkscited by 35
  5. 2025Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellencecited by 24
  6. 2023Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreachingcited by 23
  7. 2024Spectral Graph Pruning Against Over-Squashing and Over-Smoothingcited by 23
  8. 2024Cayley Graph Propagationcited by 21
  9. 2024Distinguished In Uniform: Self Attention Vs. Virtual Nodescited by 19
  10. 2024Learning Long Range Dependencies on Graphs via Random Walkscited by 18
  11. 2025Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurementcited by 18
  12. 2024Spatio-Spectral Graph Neural Networkscited by 17
38 more
  1. 2025No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasetscited by 16
  2. 2024Probabilistic Graph Rewiring via Virtual Nodescited by 15
  3. 2023Facilitating Graph Neural Networks with Random Walk on Simplicial Complexescited by 14
  4. 2024Understanding Virtual Nodes: Oversquashing and Node Heterogeneitycited by 14
  5. 2024Bundle Neural Networks for message diffusion on graphscited by 13
  6. 2024Benchmarking Positional Encodings for GNNs and Graph Transformerscited by 13
  7. 2024MANTRA: The Manifold Triangulations Assemblagecited by 12
  8. 2023Recurrent Distance Filtering for Graph Representation Learningcited by 11
  9. 2024An end-to-end attention-based approach for learning on graphscited by 11
  10. 2024The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisitedcited by 11
  11. 2024Node Identifiers: Compact, Discrete Representations for Efficient Graph Learningcited by 10
  12. 2025Cooperative Sheaf Neural Networkscited by 10
  13. 2025Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modelingcited by 9
  14. 2025On Measuring Long-Range Interactions in Graph Neural Networkscited by 9
  15. 2024Aligning Transformers with Weisfeiler-Lemancited by 8
  16. 2024Unitary convolutions for learning on graphs and groupscited by 8
  17. 2025Can You Hear Me Now? A Benchmark for Long-Range Graph Propagationcited by 8
  18. 2023Non-backtracking Graph Neural Networkscited by 7
  19. 2024On the H"older Stability of Multiset and Graph Neural Networkscited by 6
  20. 2024A Comprehensive Graph Pooling Benchmark: Effectiveness, Robustness and Generalizabilitycited by 6
  21. 2024Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graphcited by 6
  22. 2024Homomorphism Counts as Structural Encodings for Graph Learningcited by 6
  23. 2025Improving the Effective Receptive Field of Message-Passing Neural Networkscited by 6
  24. 2024Graph Unitary Message Passingcited by 5
  25. 2024Next Level Message-Passing with Hierarchical Support Graphscited by 5
  26. 2024A Cosmic-Scale Benchmark for Symmetry-Preserving Data Processingcited by 5
  27. 2025Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centralitycited by 5
  28. 2025Molecular Fingerprints Are Strong Models for Peptide Function Predictioncited by 5
  29. 2025DualEquiNet: A Dual-Space Hierarchical Equivariant Network for Large Biomoleculescited by 5
  30. 2025Molecular Machine Learning in Chemical Process Designcited by 5
  31. 2023Robustness of Algorithms for Causal Structure Learning to Hyperparameter Choicecited by 4
  32. 2024Graph as Point Setcited by 4
  33. 2024A Scalable and Effective Alternative to Graph Transformerscited by 4
  34. 2026mHC-GNN: Manifold-Constrained Hyper-Connections for Graph Neural Networkscited by 4
  35. 2026A Fair Evaluation of Graph Foundation Models for Node Property Predictioncited by 4
  36. 2024Graph External Attention Enhanced Transformercited by 3
  37. 2024MolMix: A Simple Yet Effective Baseline for Multimodal Molecular Representation Learningcited by 3
  38. 2025Plain Transformers Can be Powerful Graph Learnerscited by 2

50 most cited of 83 All 83 (JSON)