Datasets › PCQM4Mv2-LSC

PCQM4Mv2-LSC

Introduced by Weihua Hu et al. in OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs17 Mar 2021 archive 2025-07-28

PCQM4Mv2 is a quantum chemistry dataset originally curated under the PubChemQC project. Based on the PubChemQC, we define a meaningful ML task of predicting DFT-calculated HOMO-LUMO energy gap of molecules given their 2D molecular graphs. The HOMO-LUMO gap is one of the most practically-relevant quantum chemical properties of molecules since it is related to reactivity, photoexcitation, and charge transport. Moreover, predicting the quantum chemical property only from 2D molecular graphs without their 3D equilibrium structures is also practically favorable. This is because obtaining 3D equilibrium structures requires DFT-based geometry optimization, which is expensive on its own.

Benchmarks archive 2025-07-28

All 1 leaderboard 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 Regression PCQM4Mv2-LSC ESA (Edge set attention, no positional encodings) Validation MAE 0.0235 An end-to-end attention-based approach for learning on graphs davidbuterez/edge-set-attention 20 Compare

Papers archive 2025-07-28

17 shown of 17 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 17. 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
An end-to-end attention-based approach for learning on graphs 1 1 16 Feb 2024 not harvested
Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers 3 1 7 Feb 2024 ran 10 of 13 samples (3 unverified)
Topology-Informed Graph Transformer 2 1 3 Feb 2024 ran 14 of 21 samples (7 unverified; 21 pointer-only for licence)
Graph Convolutions Enrich the Self-Attention in Transformers! 1 1 7 Dec 2023 ran 19 of 29 samples (10 unverified)
The Information Pathways Hypothesis: Transformers are Dynamic Self-Ensembles 1 2 2 Jun 2023 not harvested
Graph Inductive Biases in Transformers without Message Passing 2 1 27 May 2023 ran 6 of 12 samples (6 unverified)
Graph Propagation Transformer for Graph Representation Learning 1 2 19 May 2023 ran 4 of 8 samples (4 unverified; 8 pointer-only for licence)
Highly Accurate Quantum Chemical Property Prediction with Uni-Mol+ 2 1 16 Mar 2023 ran 0 of 1 samples (1 unverified)
One Transformer Can Understand Both 2D & 3D Molecular Data 1 1 4 Oct 2022 ran 1 of 1 samples (0 unverified)
Pure Transformers are Powerful Graph Learners 2 1 6 Jul 2022 ran 7 of 7 samples (0 unverified; 7 pointer-only for licence)
Recipe for a General, Powerful, Scalable Graph Transformer 4 1 25 May 2022 ran 3 of 21 samples (18 unverified)
GRPE: Relative Positional Encoding for Graph Transformer 1 1 30 Jan 2022 ran 0 of 6 samples (6 unverified)
Global Self-Attention as a Replacement for Graph Convolution 3 2 7 Aug 2021 ran 0 of 4 samples (4 unverified)
Do Transformers Really Perform Bad for Graph Representation? 5 1 9 Jun 2021 not harvested
OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs 6 1 17 Mar 2021 not harvested
How Powerful are Graph Neural Networks? 19 1 1 Oct 2018 ran 3 of 10 samples (7 unverified; 5 pointer-only for licence)
Semi-Supervised Classification with Graph Convolutional Networks 55 1 9 Sep 2016 ran 31 of 58 samples (27 unverified; 22 pointer-only for licence)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

CC BY 4.0

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • PCQM4Mv2-LSC

1 variant name, 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