Datasets › Long Range Graph Benchmark (LRGB)

Long Range Graph Benchmark (LRGB)

Introduced by Vijay Prakash Dwivedi et al. in Long Range Graph Benchmark16 Jun 2022 archive 2025-07-28

The Long Range Graph Benchmark (LRGB) is a collection of 5 graph learning datasets that arguably require long-range reasoning to achieve strong performance in a given task. The 5 datasets in this benchmark can be used to prototype new models that can capture long range dependencies in graphs.

Dataset Domain Task
PascalVOC-SP Computer Vision Node Classification
COCO-SP Computer Vision Node Classification
PCQM-Contact Quantum Chemistry Link Prediction
Peptides-func Chemistry Graph Classification
Peptides-struct Chemistry Graph Regression

Benchmarks archive 2025-07-28

All 4 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Graph Classification Peptides-func ESA + RWSE (Edge set attention, Random Walk Structural Encoding, + validation set) AP 0.7479 An end-to-end attention-based approach for learning on graphs davidbuterez/edge-set-attention 44 Compare
Graph Regression Peptides-struct ESA + RWSE (Edge set attention, Random Walk Structural Encoding, tuned) MAE 0.2393±0.0004 An end-to-end attention-based approach for learning on graphs davidbuterez/edge-set-attention 39 Compare
Node Classification COCO-SP NeuralWalker macro F1 0.4398 ± 0.0033 Learning Long Range Dependencies on Graphs via Random Walks borgwardtlab/neuralwalker 19 Compare
Link Prediction PCQM-Contact ViT-PS Hits@1 0.3287 Learning Probabilistic Symmetrization for Architecture... jw9730/lps 18 Compare

Papers archive 2025-07-28

30 shown of 32 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 76. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Improving the Effective Receptive Field of Message-Passing Neural Networks 1 2 29 May 2025 ran 1 of 1 samples (0 unverified)
Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence 1 3 13 Feb 2025 ran 4 of 12 samples (8 unverified)
Molecular Fingerprints Are Strong Models for Peptide Function Prediction 4 6 29 Jan 2025 not harvested
From Primes to Paths: Enabling Fast Multi-Relational Graph Analysis 1 1 17 Nov 2024 not harvested
Molecular Topological Profile (MOLTOP) - Simple and Strong Baseline for Molecular Graph Classification 1 1 17 Oct 2024 not harvested
Next Level Message-Passing with Hierarchical Support Graphs 1 3 22 Jun 2024 ran 4 of 10 samples (6 unverified)
PANDA: Expanded Width-Aware Message Passing Beyond Rewiring 1 2 6 Jun 2024 ran 7 of 9 samples (2 unverified)
Learning Long Range Dependencies on Graphs via Random Walks 1 4 5 Jun 2024 ran 13 of 13 samples (0 unverified)
Spatio-Spectral Graph Neural Networks 1 1 29 May 2024 ran 7 of 9 samples (2 unverified)
CKGConv: General Graph Convolution with Continuous Kernels 1 2 21 Apr 2024 ran 8 of 11 samples (3 unverified; 11 pointer-only for licence)
An end-to-end attention-based approach for learning on graphs 1 6 16 Feb 2024 not harvested
Topology-Informed Graph Transformer 2 2 3 Feb 2024 ran 14 of 21 samples (7 unverified; 21 pointer-only for licence)
Graph Transformers without Positional Encodings 0 2 31 Jan 2024 not harvested
Recurrent Distance Filtering for Graph Representation Learning 1 2 3 Dec 2023 ran 12 of 21 samples (9 unverified; 21 pointer-only for licence)
Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark 2 16 1 Sep 2023 ran 5 of 12 samples (7 unverified)
Enhancing Graph Transformers with Hierarchical Distance Structural Encoding 1 1 22 Aug 2023 ran 0 of 1 samples (1 unverified)
Neural Priority Queues for Graph Neural Networks 0 1 18 Jul 2023 not harvested
Path Neural Networks: Expressive and Accurate Graph Neural Networks 1 2 9 Jun 2023 ran 2 of 2 samples (0 unverified)
CIN++: Enhancing Topological Message Passing 1 2 6 Jun 2023 not harvested
Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance 1 3 5 Jun 2023 ran 0 of 13 samples (13 unverified)
Graph Inductive Biases in Transformers without Message Passing 2 2 27 May 2023 ran 6 of 12 samples (6 unverified)
DRew: Dynamically Rewired Message Passing with Delay 1 3 13 May 2023 ran 2 of 9 samples (7 unverified)
Exphormer: Sparse Transformers for Graphs 1 4 10 Mar 2023 ran 1 of 1 samples (0 unverified)
Diffusing Graph Attention 0 3 1 Mar 2023 not harvested
Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures 2 2 17 Feb 2023 ran 3 of 5 samples (2 unverified)
On the Connection Between MPNN and Graph Transformer 1 2 27 Jan 2023 not harvested
A Generalization of ViT/MLP-Mixer to Graphs 3 4 27 Dec 2022 ran 2 of 3 samples (1 unverified)
Pure Transformers are Powerful Graph Learners 2 1 6 Jul 2022 ran 7 of 7 samples (0 unverified; 7 pointer-only for licence)
Long Range Graph Benchmark 2 28 16 Jun 2022 not harvested
Recipe for a General, Powerful, Scalable Graph Transformer 4 4 25 May 2022 ran 3 of 21 samples (18 unverified)

The full list of 32 is in the JSON twin.

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Custom

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • Long Range Graph Benchmark (LRGB)
  • PascalVOC-SP
  • COCO-SP
  • Peptides-func
  • Peptides-struct
  • PCQM-Contact

6 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections