Meta-Learning GNN Initializations for Low-Resource Molecular Property Prediction
Building $\textit{in silico}$ models to predict chemical properties and activities is a crucial step in drug discovery. However, limited labeled data often hinders the application of deep learning in this setting. Meanwhile advances in meta-learning have enabled state-of-the-art performances in few-shot learning benchmarks, naturally prompting the question: Can meta-learning improve deep learning performance in low-resource drug discovery projects? In this work, we assess the transferability of graph neural networks initializations learned by the Model-Agnostic Meta-Learning (MAML) algorithm - and its variants FO-MAML and ANIL - for chemical properties and activities tasks. Using the ChEMBL20 dataset to emulate low-resource settings, our benchmark shows that meta-initializations perform comparably to or outperform multi-task pre-training baselines on 16 out of 20 in-distribution tasks and on all out-of-distribution tasks, providing an average improvement in AUPRC of 11.2% and 26.9% respectively. Finally, we observe that meta-initializations consistently result in the best performing models across fine-tuning sets with $k \in \{16, 32, 64, 128, 256\}$ instances.
Code (0)
등록된 구현이 없습니다.
Tasks
Drug DiscoveryFew-Shot LearningMeta-LearningMolecular Property PredictionProperty PredictionSimilar Papers 제목 키워드 기반
Few-Shot Graph Learning for Molecular Property Prediction
The recent success of graph neural networks has significantly boosted molecular property prediction, advancing activities such as drug discovery. The existing deep neural network methods usually require large training da…
AttributeDrug DiscoveryGraph LearningGraph Neural Network+7Graph Sampling-based Meta-Learning for Molecular Property Prediction
Molecular property is usually observed with a limited number of samples, and researchers have considered property prediction as a few-shot problem. One important fact that has been ignored by prior works is that each mol…
Graph SamplingMeta-LearningMolecular Property PredictionProperty PredictionProperty-Aware Relation Networks for Few-Shot Molecular Property Prediction
Molecular property prediction plays a fundamental role in drug discovery to identify candidate molecules with target properties. However, molecular property prediction is essentially a few-shot problem which makes it har…
Drug DiscoveryGraph LearningMeta-LearningMolecular Property Prediction+3In-Context Learning for Few-Shot Molecular Property Prediction
In-context learning has become an important approach for few-shot learning in Large Language Models because of its ability to rapidly adapt to new tasks without fine-tuning model parameters. However, it is restricted to …
Few-Shot LearningIn-Context LearningMeta-LearningMolecular Property Prediction+2Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction
We propose Adaptive Deep Kernel Fitting with Implicit Function Theorem (ADKF-IFT), a novel framework for learning deep kernel Gaussian processes (GPs) by interpolating between meta-learning and conventional deep kernel l…
Bilevel OptimizationDrug DiscoveryGaussian ProcessesMeta-Learning+2