mlsanityData to 7 Oct 2026

CalibHyper: Chance-Corrected Relational Hypergraphs for Few-Shot Molecular Property Prediction

arXiv 2609.33342 ↗First posted 27 Sep 2026cs.LG cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Molecular property prediction is central to drug development and materials discovery, but experiments are costly and labeled data are scarce. Context-aware methods use auxiliary assay labels to support few-shot prediction, and recent work supervises property relations with label agreement. However, label agreement is sensitive to class marginals and does not directly capture dependence between properties. We propose CalibHyper, a chance-corrected relational hypergraph method based on the joint label distribution. CalibHyper subtracts an independence baseline from the ordered four-state label distribution and shrinks the residual according to the number of joint observations. A swap-equivariant relation head estimates these residuals, which choose the auxiliary properties for each molecule and set the sign and weight of their hyperedge messages. On thirteen datasets from five benchmarks, in both 1-shot and 10-shot settings, CalibHyper and its ablation settings achieve ROC-AUC competitive with the strongest reported results.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 66 references that are in the map. First posted on arXiv 27 Sep 2026.

Builds on

43 of 66 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Layer Normalizationcited by 5,579
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  7. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  8. 2016Group Equivariant Convolutional Networkscited by 1,154
  9. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  10. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  11. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  12. 2018Hypergraph Neural Networkscited by 482
31 more
  1. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 318
  2. 2020ReZero is All You Need: Fast Convergence at Large Depthcited by 260
  3. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 239
  4. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  5. 2021Accounting for Variance in Machine Learning Benchmarkscited by 195
  6. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 124
  7. 2019Edge-labeling Graph Neural Network for Few-shot Learningcited by 114
  8. 2016Low Data Drug Discovery with One-shot Learningcited by 91
  9. 2021Few-Shot Graph Learning for Molecular Property Predictioncited by 81
  10. 2019Dynamic Graph Message Passing Networkscited by 62
  11. 2015Massively Multitask Networks for Drug Discoverycited by 49
  12. 2021Meta-Learning with Fewer Tasks through Task Interpolationcited by 45
  13. 2021Property-Aware Relation Networks for Few-Shot Molecular Property Predictioncited by 41
  14. 2024Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Treescited by 30
  15. 2023Conditional Graph Information Bottleneck for Molecular Relational Learningcited by 24
  16. 2023Context-enriched molecule representations improve few-shot drug discoverycited by 23
  17. 2023Interpretable Prototype-based Graph Information Bottleneckcited by 23
  18. 2022Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Predictioncited by 21
  19. 2023Graph Sampling-based Meta-Learning for Molecular Property Predictioncited by 10
  20. 2024Learning Molecular Representation in a Cellcited by 8
  21. 2023In-Context Learning for Few-Shot Molecular Property Predictioncited by 7
  22. 2024Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Taskscited by 7
  23. 2025Dual-level Mixup for Graph Few-shot Learning with Fewer Taskscited by 5
  24. 2023PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Predictioncited by 4
  25. 2024Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Predictioncited by 4
  26. 2023Learning to Group Auxiliary Datasets for Moleculecited by 3
  27. 2025UniMatch: Universal Matching from Atom to Task for Few-Shot Drug Discoverycited by 3
  28. 2024Knowledge-enhanced Relation Graph and Task Sampling for Few-shot Molecular Property Predictioncited by 2
  29. 2025Few-shot Molecular Property Prediction: A Surveycited by 1
  30. 2026Context-aware Graph Causality Inference for Few-Shot Molecular Property Predictioncited by 1
  31. 2026ReCoG: Relational and Compact Context Graph Learning for Few-shot Molecular Property Predictioncited by 1

Built on by

Not cited yet.