Graph Neural Network Expressivity and Meta-Learning for Molecular Property Regression
Not on the map. Why?
Abstract (arXiv)
We demonstrate the applicability of model-agnostic algorithms for meta-learning, specifically Reptile, to GNN models in molecular regression tasks. Using meta-learning we are able to learn new chemical prediction tasks with only a few model updates, as compared to using randomly initialized GNNs which require learning each regression task from scratch. We experimentally show that GNN layer expressivity is correlated to improved meta-learning. Additionally, we also experiment with GNN emsembles which yield best performance and rapid convergence for k-shot learning.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 29 of its 47 references that are in the map. First posted on arXiv 24 Sep 2022.
Builds on
29 of 47 references.
References · 29
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
- 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
- 2018On First-Order Meta-Learning Algorithmscited by 1,003
- 2021E(n) Equivariant Graph Neural Networkscited by 951
- 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
- 2018How to train your MAMLcited by 306
- 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
- 2020GraphNorm: A Principled Approach to Accelerating Graph Neural Network Trainingcited by 116
- 2018Meta-Learning for Low-Resource Neural Machine Translationcited by 105
- 2017Building machines that adapt and compute like brainscited by 99
17 more
- 2020Graph Meta Learning via Local Subgraphscited by 89
- 2021Few-Shot Graph Learning for Molecular Property Predictioncited by 81
- 2021Few-shot Network Anomaly Detection via Cross-network Meta-learningcited by 64
- 2022Message passing all the way upcited by 47
- 2021Adaptive-Control-Oriented Meta-Learning for Nonlinear Systemscited by 38
- 2019Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Modelscited by 36
- 2019MetaPred: Meta-Learning for Clinical Risk Prediction with Limited Patient Electronic Health Recordscited by 33
- 2020Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measurescited by 31
- 2019Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systemscited by 25
- 2020Fast Online Adaptation in Robotics through Meta-Learning Embeddings of Simulated Priorscited by 21
- 2021Meta-Inductive Node Classification across Graphscited by 16
- 2021A Meta-Learning Approach for Training Explainable Graph Neural Networkscited by 15
- 2017Meta-QSAR: a large-scale application of meta-learning to drug design and discoverycited by 10
- 2020A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settingscited by 8
- 2021Meta-Learning with Graph Neural Networks: Methods and Applicationscited by 7
- 2020Meta-Learning GNN Initializations for Low-Resource Molecular Property Predictioncited by 6
- 2021Structure-Enhanced Meta-Learning For Few-Shot Graph Classificationcited by 4
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.