English
Related papers

Related papers: Uncertainty Estimation for Molecules: Desiderata a…

200 papers

Graph neural networks (GNNs) are a popular class of machine learning models whose major advantage is their ability to incorporate a sparse and discrete dependency structure between data points. Unfortunately, GNNs can only be used when such…

Machine Learning · Computer Science 2020-06-22 Luca Franceschi , Mathias Niepert , Massimiliano Pontil , Xiao He

Recently, Knowledge Graphs (KGs) have been successfully coupled with Large Language Models (LLMs) to mitigate their hallucinations and enhance their reasoning capability, such as in KG-based retrieval-augmented frameworks. However, current…

Artificial Intelligence · Computer Science 2024-10-22 Bo Ni , Yu Wang , Lu Cheng , Erik Blasch , Tyler Derr

In this work, we study the influence of domain-specific characteristics when defining a meaningful notion of predictive uncertainty on graph data. Previously, the so-called Graph Posterior Network (GPN) model has been proposed to quantify…

Machine Learning · Computer Science 2024-09-09 Clemens Damke , Eyke Hüllermeier

Predicting molecular properties (e.g., atomization energy) is an essential issue in quantum chemistry, which could speed up much research progress, such as drug designing and substance discovery. Traditional studies based on density…

Computational Physics · Physics 2019-08-20 Chengqiang Lu , Qi Liu , Chao Wang , Zhenya Huang , Peize Lin , Lixin He

This paper derives statistical guarantees for the performance of Graph Neural Networks (GNNs) in link prediction tasks on graphs generated by a graphon. We propose a linear GNN architecture (LG-GNN) that produces consistent estimators for…

Machine Learning · Computer Science 2024-02-08 Alan Chung , Amin Saberi , Morgane Austern

Multitude of deep learning models have been proposed for node classification in graphs. However, they tend to perform poorly under labeled-data scarcity. Although Few-shot learning for graphs has been introduced to overcome this problem,…

Machine Learning · Computer Science 2026-02-02 Appan Rakaraddi , Lam Siew-Kei , Mahardhika Pratama , Marcus de Carvalho

We present a systematic investigation using graph neural networks (GNNs) to model organic chemical reactions. To do so, we prepared a dataset collection of four ubiquitous reactions from the organic chemistry literature. We evaluate seven…

Machine Learning · Computer Science 2020-07-10 Serim Ryou , Michael R. Maser , Alexander Y. Cui , Travis J. DeLano , Yisong Yue , Sarah E. Reisman

Machine learning models are increasingly used to predict material properties and accelerate atomistic simulations, but the reliability of their predictions depends on the representativeness of the training data. We present a scalable,…

Chemical Physics · Physics 2025-10-20 Daniel Willimetz , Lukáš Grajciar

We apply a temporal edge prediction model for weighted dynamic graphs to predict time-dependent changes in molecular structure. Each molecule is represented as a complete graph in which each atom is a vertex and all vertex pairs are…

Machine Learning · Computer Science 2021-06-28 Michael Hunter Ashby , Jenna A. Bilbrey

The usual figure of merit characterizing the performance of neural networks applied to problems in the quantum domain is their accuracy, being the probability of a correct answer on a previously unseen input. Here we append this parameter…

Quantum Physics · Physics 2022-12-29 Jan Wasilewski , Tomasz Paterek , Karol Horodecki

Inverse problems and, in particular, inferring unknown or latent parameters from data are ubiquitous in engineering simulations. A predominant viewpoint in identifying unknown parameters is Bayesian inference where both prior information…

Computation · Statistics 2022-08-31 Vahid Keshavarzzadeh , Robert M. Kirby , Akil Narayan

Uncertainty quantification (UQ) in graph neural networks (GNNs) is crucial in high-stakes domains but remains a significant challenge. In graph settings, message passing often relies on strong assumptions such as exchangeability, which are…

Machine Learning · Computer Science 2026-05-07 Soyoung park , Hwanjun Song , Sungsu Lim

Accurate modelling and quantification of predictive uncertainty is crucial in deep learning since it allows a model to make safer decisions when the data is ambiguous and facilitates the users' understanding of the model's confidence in its…

Machine Learning · Statistics 2025-08-26 Soumyasundar Pal , Liheng Ma , Amine Natik , Yingxue Zhang , Mark Coates

As they carry great potential for modeling complex interactions, graph neural network (GNN)-based methods have been widely used to predict quantum mechanical properties of molecules. Most of the existing methods treat molecules as molecular…

Machine Learning · Computer Science 2020-09-29 Zeren Shui , George Karypis

Deep learning has emerged as a promising paradigm to give access to highly accurate predictions of molecular and materials properties. A common short-coming shared by current approaches, however, is that neural networks only give point…

Computational Physics · Physics 2023-05-10 Albert Zhu , Simon Batzner , Albert Musaelian , Boris Kozinsky

This paper presents a probabilistic framework to obtain both reliable and fast uncertainty estimates for predictions with Deep Neural Networks (DNNs). Our main contribution is a practical and principled combination of DNNs with sparse…

Robotics · Computer Science 2021-09-22 Jongseok Lee , Jianxiang Feng , Matthias Humt , Marcus G. Müller , Rudolph Triebel

Uncertainty quantification (UQ) in scientific machine learning is increasingly critical as neural networks are widely adopted to tackle complex problems across diverse scientific disciplines. For physics-informed neural networks (PINNs), a…

Machine Learning · Statistics 2025-10-20 Frank Shih , Zhenghao Jiang , Faming Liang

Uncertainty quantification is crucial for building reliable and trustable machine learning systems. We propose to estimate uncertainty in recurrent neural networks (RNNs) via stochastic discrete state transitions over recurrent timesteps.…

Machine Learning · Computer Science 2020-11-25 Cheng Wang , Carolin Lawrence , Mathias Niepert

Uncertainty quantification has become an important factor in understanding the data representations produced by Graph Neural Networks (GNNs). Despite their predictive capabilities being ever useful across industrial workspaces, the inherent…

Artificial Intelligence · Computer Science 2026-05-13 Tommy Woodley , Shireen Kudukkil Manchingal , Matteo Tolloso , Davide Bacciu , Fabio Cuzzolin

Graph Neural Networks (GNNs) have shown considerable success in neural algorithmic reasoning. Many traditional algorithms make use of an explicit memory in the form of a data structure. However, there has been limited exploration on…

Machine Learning · Computer Science 2023-07-20 Rishabh Jain , Petar Veličković , Pietro Liò