mlsanityData to 7 Oct 2026

Enhancing Molecular Property Predictions by Learning from Bond Modelling and Interactions

arXiv 2603.00568 ↗First posted 28 Feb 2026cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Molecule representation learning is crucial for understanding and predicting molecular properties. However, conventional atom-centric models, which treat chemical bonds merely as pairwise interactions, often overlook complex bond-level phenomena like resonance and stereoselectivity. This oversight limits their predictive accuracy for nuanced chemical behaviors. To address this limitation, we introduce DeMol, a dual-graph framework whose architecture is motivated by a rigorous information-theoretic analysis demonstrating the information gain from a bond-centric perspective. DeMol explicitly models molecules through parallel atom-centric and bond-centric channels. These are synergistically fused by multi-scale Double-Helix Blocks designed to learn intricate atom-atom, atom-bond, and bond-bond interactions. The framework's geometric consistency is further enhanced by a regularization term based on covalent radii to enforce chemically plausible structures. Comprehensive evaluations on diverse benchmarks, including PCQM4Mv2, OC20 IS2RE, QM9, and MoleculeNet, show that DeMol establishes a new state-of-the-art, outperforming existing methods. These results confirm the superiority of explicitly modelling bond information and interactions, paving the way for more robust and accurate molecular machine learning.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 61 of its 88 references that are in the map. First posted on arXiv 28 Feb 2026.

Builds on

61 of 88 references.

References · 61

  1. 2018How Powerful are Graph Neural Networks?cited by 4,355
  2. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  3. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  4. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  5. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  6. 2021E(n) Equivariant Graph Neural Networkscited by 951
  7. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  8. 2019Graph Neural Networks for Social Recommendationcited by 711
  9. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 702
  10. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
  11. 2020Directional Message Passing for Molecular Graphscited by 556
  12. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
38 more
  1. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  2. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
  3. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 342
  4. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 328
  5. 2019Cormorant: Covariant Molecular Neural Networkscited by 262
  6. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 258
  7. 2020DeeperGCN: All You Need to Train Deeper GCNscited by 249
  8. 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248
  9. 2020The Open Catalyst 2020 (OC20) Dataset and Community Challengescited by 246
  10. 2021ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Predictioncited by 204
  11. 2022Pure Transformers are Powerful Graph Learnerscited by 188
  12. 2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 188
  13. 2022TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentialscited by 179
  14. 2021Spherical Message Passing for 3D Graph Networkscited by 166
  15. 20213D Infomax improves GNNs for Molecular Property Predictioncited by 146
  16. 2021Global Self-Attention as a Replacement for Graph Convolutioncited by 113
  17. 2020LieTransformer: Equivariant self-attention for Lie Groupscited by 100
  18. 2023Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspectivecited by 91
  19. 2025A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Modelscited by 87
  20. 2023Generative Diffusion Models on Graphs: Methods and Applicationscited by 79
  21. 2022One Transformer Can Understand Both 2D & 3D Molecular Datacited by 77
  22. 2022GRPE: Relative Positional Encoding for Graph Transformercited by 67
  23. 2022Benchmarking Graphormer on Large-Scale Molecular Modeling Datasetscited by 63
  24. 2025Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendationcited by 56
  25. 2021Graph Trend Filtering Networks for Recommendationscited by 53
  26. 2022Graph-based Molecular Representation Learningcited by 51
  27. 2021Simple GNN Regularisation for 3D Molecular Property Prediction & Beyondcited by 44
  28. 2022Energy-Motivated Equivariant Pretraining for 3D Molecular Graphscited by 37
  29. 2024TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendationcited by 35
  30. 2020Graph convolutions that can finally model local structurecited by 31
  31. 2024Linear-Time Graph Neural Networks for Scalable Recommendationscited by 31
  32. 2022GPS++: An Optimised Hybrid MPNN/Transformer for Molecular Property Predictioncited by 28
  33. 2022Towards Training Billion Parameter Graph Neural Networks for Atomic Simulationscited by 25
  34. 2023Automated 3D Pre-Training for Molecular Property Predictioncited by 24
  35. 2023Highly Accurate Quantum Chemical Property Prediction with Uni-Mol+cited by 22
  36. 2024Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generationcited by 22
  37. 2025CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agentcited by 22
  38. 2024Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformerscited by 12

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Geometric Flow Matching for Molecular Conformation Generation via Manifold Decompositioncited by 3
  2. 2026Multi-level Self-supervised Pretraining on Compositional Hierarchical Graph for Molecular Property Predictioncited by 0
  3. 2026Unlocking Multimodal Protein Language Models at Inference Timecited by 0