Improved Uncertainty Estimation of Graph Neural Network Potentials Using Engineered Latent Space Distances
원문 초록
Graph neural networks (GNNs) have been shown to be astonishingly capable models for molecular property prediction, particularly as surrogates for expensive density functional theory calculations of relaxed energy for novel material discovery. However, one limitation of GNNs in this context is the lack of useful uncertainty prediction methods, as this is critical to the material discovery pipeline. In this work, we show that uncertainty quantification for relaxed energy calculations is more complex than uncertainty quantification for other kinds of molecular property prediction, due to the effect that structure optimizations have on the error distribution. We propose that distribution-free techniques are more useful tools for assessing calibration, recalibrating, and developing uncertainty prediction methods for GNNs performing relaxed energy calculations. We also develop a relaxed energy task for evaluating uncertainty methods for equivariant GNNs, based on distribution-free recalibration and using the Open Catalyst Project dataset. We benchmark a set of popular uncertainty prediction methods on this task, and show that latent distance methods, with our novel improvements, are the most well-calibrated and economical approach for relaxed energy calculations. Finally, we demonstrate that our latent space distance method produces results which align with our expectations on a clustering example, and on specific equation of state and adsorbate coverage examples from outside the training dataset.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Descriptor-based Foundation Models for Molecular Property Prediction
Graph Neural Networks in Modern AI-aided Drug Discovery
Robust Molecular Property Prediction via Densifying Scarce Labeled Data
The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learning
AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction
High Order Collaboration-Oriented Federated Graph Neural Network for Accurate QoS Prediction
토론
이 논문과 연결된 포럼 글이 아직 없습니다.