Related papers: GraphRT: A graph-based deep learning model for pre…

Predicting relaxed atomic structures of chemically complex materials remains a major computational challenge, particularly for high-entropy systems where traditional first-principles methods become prohibitively expensive. We introduce the…

Increased attention has been paid over the last four years to dynamic network embedding. Existing dynamic embedding methods, however, consider the problem as limited to the evolution of a topology over a sequence of global, discrete states.…

Raman spectroscopy is an important tool in the study of vibrational properties and composition of molecules, peptides and even proteins. Raman spectra can be simulated based on the change of the electronic polarizability with vibrations,…

Matrix completion models are among the most common formulations of recommender systems. Recent works have showed a boost of performance of these techniques when introducing the pairwise relationships between users/items in the form of…

Retention time drift caused by fluctuations in physical factors such as temperature ramping rate and carrier gas flow rate is ubiquitous in chromatographic measurements. Proper peak identification and alignment across different…

Graph embedding methods aim at finding useful graph representations by mapping nodes to a low-dimensional vector space. It is a task with important downstream applications, such as link prediction, graph reconstruction, data visualization,…

Graph Neural Networks (GNNs) have recently become increasingly popular due to their ability to learn complex systems of relations or interactions arising in a broad spectrum of problems ranging from biology and particle physics to social…

Graphs are a useful abstraction of image content. Not only can graphs represent details about individual objects in a scene but they can capture the interactions between pairs of objects. We present a method for training a convolutional…

Designing accurate deep learning models for molecular property prediction plays an increasingly essential role in drug and material discovery. Recently, due to the scarcity of labeled molecules, self-supervised learning methods for learning…

Many machine learning techniques have been proposed in the last few years to process data represented in graph-structured form. Graphs can be used to model several scenarios, from molecules and materials to RNA secondary structures. Several…

Electronic medical record (EMR) data contains historical sequences of visits of patients, and each visit contains rich information, such as patient demographics, hospital utilisation and medical codes, including diagnosis, procedure and…

Traffic forecasting is the foundation for intelligent transportation systems. Spatiotemporal graph neural networks have demonstrated state-of-the-art performance in traffic forecasting. However, these methods do not explicitly model some of…

Graph deep learning methods have become popular tools to process collections of correlated time series. Unlike traditional multivariate forecasting methods, graph-based predictors leverage pairwise relationships by conditioning forecasts on…

This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs. First, we use localized node embeddings computed by a graph neural network to obtain an initial ranking of soft…

The graph structure is a commonly used data storage mode, and it turns out that the low-dimensional embedded representation of nodes in the graph is extremely useful in various typical tasks, such as node classification, link prediction ,…

Online continual learning for image classification is crucial for models to adapt to new data while retaining knowledge of previously learned tasks. This capability is essential to address real-world challenges involving dynamic…

Deep Recurrent Neural Network architectures, though remarkably capable at modeling sequences, lack an intuitive high-level spatio-temporal structure. That is while many problems in computer vision inherently have an underlying high-level…

The application of large language models (LLMs) to graph data has attracted a lot of attention recently. LLMs allow us to use deep contextual embeddings from pretrained models in text-attributed graphs, where shallow embeddings are often…

The dominant graph neural networks (GNNs) over-rely on the graph links, several serious performance problems with which have been witnessed already, e.g., suspended animation problem and over-smoothing problem. What's more, the inherently…

Particle physics is a branch of science aiming at discovering the fundamental laws of matter and forces. Graph neural networks are trainable functions which operate on graphs---sets of elements and their pairwise relations---and are a…