Knowledge-enhanced Relation Graph and Task Sampling for Few-shot Molecular Property Prediction
Not on the map. Why?
Abstract (arXiv)
Recently, few-shot molecular property prediction (FSMPP) has garnered increasing attention. Despite impressive breakthroughs achieved by existing methods, they often overlook the inherent many-to-many relationships between molecules and properties, which limits their performance. For instance, similar substructures of molecules can inspire the exploration of new compounds. Additionally, the relationships between properties can be quantified, with high-related properties providing more information in exploring the target property than those low-related. To this end, this paper proposes a novel meta-learning FSMPP framework (KRGTS), which comprises the Knowledge-enhanced Relation Graph module and the Task Sampling module. The knowledge-enhanced relation graph module constructs the molecule-property multi-relation graph (MPMRG) to capture the many-to-many relationships between molecules and properties. The task sampling module includes a meta-training task sampler and an auxiliary task sampler, responsible for scheduling the meta-training process and sampling high-related auxiliary tasks, respectively, thereby achieving efficient meta-knowledge learning and reducing noise introduction. Empirically, extensive experiments on five datasets demonstrate the superiority of KRGTS over a variety of state-of-the-art methods. The code is available in https://github.com/Vencent-Won/KRGTS-public.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 25 of its 47 references that are in the map. First posted on arXiv 24 May 2024.
Builds on
25 of 47 references.
References · 25
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2018How Powerful are Graph Neural Networks?cited by 4,355
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
- 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
- 2019Strategies for Pre-training Graph Neural Networkscited by 964
- 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
- 2021ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Predictioncited by 204
- 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
- 2019Edge-labeling Graph Neural Network for Few-shot Learningcited by 114
- 2016Low Data Drug Discovery with One-shot Learningcited by 91
13 more
- 2021Few-Shot Graph Learning for Molecular Property Predictioncited by 81
- 2021GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Predictioncited by 61
- 2020ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Predictioncited by 58
- 2019Dense Classification and Implanting for Few-Shot Learningcited by 56
- 2018PotentialNet for Molecular Property Predictioncited by 46
- 2021Property-Aware Relation Networks for Few-Shot Molecular Property Predictioncited by 41
- 2022KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Predictioncited by 31
- 2020Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Propertiescited by 30
- 2021Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developmentscited by 23
- 2021LibFewShot: A Comprehensive Library for Few-shot Learningcited by 21
- 2022Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Predictioncited by 21
- 2023Graph Sampling-based Meta-Learning for Molecular Property Predictioncited by 10
- 2024Multi-Modal Representation Learning for Molecular Property Prediction: Sequence, Graph, Geometrycited by 10
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.